AnishDev commited on
Commit
13644b0
Β·
1 Parent(s): a7a9afe

minimal changes

Browse files
fly.toml DELETED
@@ -1,66 +0,0 @@
1
- # fly.toml app configuration file generated for coderound-matching-api
2
- #
3
- # See https://fly.io/docs/reference/configuration/ for information about how to use this file.
4
- #
5
-
6
- app = "coderound-matching-api"
7
- primary_region = "iad"
8
-
9
- [build]
10
-
11
- # Environment variables are set as secrets in Fly.io
12
- # Use `fly secrets set KEY=VALUE` to set them.
13
- # Example:
14
- # fly secrets set REDIS_URL="redis://user:pass@host:port"
15
- # fly secrets set CORS_ORIGINS="http://localhost:3000,https://your-frontend.com"
16
- # fly secrets set OLLAMA_HOST="https://your-ollama-instance.com" OLLAMA_API_KEY="your-key"
17
-
18
- [env]
19
- PORT = "8000"
20
- # Default log level, can be overridden by secrets
21
- LOG_LEVEL = "INFO"
22
- # Default embedding model, can be overridden by secrets
23
- EMBEDDING_MODEL = "all-MiniLM-L6-v2"
24
-
25
- [http_service]
26
- internal_port = 8000
27
- force_https = true
28
- auto_stop_machines = "off"
29
- auto_start_machines = true
30
- min_machines_running = 1
31
- processes = ["app"]
32
-
33
- [[vm]]
34
- memory = "2gb"
35
- cpu_kind = "shared"
36
- cpus = 2
37
-
38
- # No persistent volume is needed as state is managed by Redis.
39
- # [mounts]
40
-
41
- [[services]]
42
- protocol = "tcp"
43
- internal_port = 8000
44
-
45
- [[services.ports]]
46
- port = 80
47
- handlers = ["http"]
48
- force_https = true
49
-
50
- [[services.ports]]
51
- port = 443
52
- handlers = ["tls", "http"]
53
-
54
- [services.concurrency]
55
- type = "connections"
56
- hard_limit = 25
57
- soft_limit = 20
58
-
59
- # Health check to ensure the service is responsive
60
- [[services.http_checks]]
61
- interval = "30s"
62
- timeout = "5s"
63
- grace_period = "60s"
64
- method = "get"
65
- path = "/health"
66
- protocol = "http"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
sample_data/generate_sample_data.py DELETED
@@ -1,551 +0,0 @@
1
- """
2
- Generates sample_candidates.xlsx for testing the JD Candidate Matching System.
3
-
4
- Run from the sample_data/ directory:
5
- python generate_sample_data.py
6
-
7
- Produces: sample_candidates.xlsx (15 candidates, mix of AI and Backend Engineers)
8
-
9
- Column schema matches the expected XLSX format:
10
- name, parsed_skills, parsed_summary, parsed_work_experience,
11
- parsed_metadata_calculated_years_experience, engineer_type,
12
- current_position, current_title, gen_ai_experience,
13
- is_actively_or_passively_looking, parsed_metadata_most_recent_company,
14
- notice_period
15
- """
16
- import openpyxl
17
- from openpyxl.styles import Font, PatternFill, Alignment
18
- from pathlib import Path
19
-
20
-
21
- def we(company, role, duration, description):
22
- """Format a single work experience entry as Python dict literal."""
23
- desc = description.replace("'", "\\'")
24
- return f"{{'company': '{company}', 'role': '{role}', 'duration': '{duration}', 'description': '{desc}'}}"
25
-
26
-
27
- CANDIDATES = [
28
- # ── AI Engineers ─────────────────────────────────────────────────────────
29
- {
30
- "id": "AI-001",
31
- "name": "Priya Sharma",
32
- "engineer_type": "AI Engineer",
33
- "current_position": "Senior AI Engineer",
34
- "current_title": "Senior AI Engineer",
35
- "parsed_metadata_calculated_years_experience": 5.5,
36
- "parsed_metadata_most_recent_company": "Google India",
37
- "gen_ai_experience": "2+ years",
38
- "is_actively_or_passively_looking": True,
39
- "notice_period": "30 days",
40
- "parsed_skills": (
41
- "Python (Expert), LangChain (Advanced), RAG pipelines (Advanced), "
42
- "PyTorch (Advanced), HuggingFace Transformers (Advanced), "
43
- "FastAPI (Core), Vector Databases - Pinecone FAISS (Advanced), "
44
- "LLM fine-tuning (Core), AWS SageMaker (Core), Docker (Core)"
45
- ),
46
- "parsed_summary": (
47
- "AI Engineer with 5+ years building production ML systems. "
48
- "Led RAG pipeline for Google Search quality team. "
49
- "Published research on LLM evaluation metrics."
50
- ),
51
- "parsed_work_experience": ", ".join([
52
- we("Google India", "Senior AI Engineer", "2.5 years",
53
- "Led RAG pipeline design serving 10M queries/day. Fine-tuned LLaMA 3 on domain-specific corpora. "
54
- "Built LangChain agents for automated QA. Used Pinecone for vector search. Deployed on GCP Vertex AI."),
55
- we("Flipkart AI Labs", "ML Engineer", "2 years",
56
- "Built recommendation models using PyTorch. Developed FastAPI inference service. "
57
- "RAG-based product Q&A system using FAISS. LLM prompt engineering for catalog enrichment."),
58
- we("Infosys AI Studio", "Junior ML Engineer", "1 year",
59
- "Trained NLP classification models with HuggingFace. Deployed models on AWS SageMaker. "
60
- "Experimented with GPT-3 embeddings for semantic search."),
61
- ]),
62
- },
63
- {
64
- "id": "AI-002",
65
- "name": "Rahul Mehta",
66
- "engineer_type": "AI Engineer",
67
- "current_position": "AI Engineer",
68
- "current_title": "AI Engineer",
69
- "parsed_metadata_calculated_years_experience": 4.0,
70
- "parsed_metadata_most_recent_company": "Swiggy",
71
- "gen_ai_experience": "1.5 years - 2 years",
72
- "is_actively_or_passively_looking": True,
73
- "notice_period": "45 days",
74
- "parsed_skills": (
75
- "Python (Core), TensorFlow (Advanced), FastAPI (Core), "
76
- "LangChain (Basic), OpenAI API (Core), "
77
- "PostgreSQL (Core), Redis (Basic), Docker (Basic), AWS (Basic)"
78
- ),
79
- "parsed_summary": (
80
- "AI Engineer at Swiggy building demand forecasting and LLM-powered "
81
- "chatbot systems. Experience with LLM APIs and RAG architectures."
82
- ),
83
- "parsed_work_experience": ", ".join([
84
- we("Swiggy", "AI Engineer", "2 years",
85
- "Built LLM-powered customer support chatbot using OpenAI GPT-4 and LangChain. "
86
- "Integrated RAG with Redis vector store. Developed FastAPI endpoints for real-time inference. "
87
- "Demand forecasting using TensorFlow time-series models."),
88
- we("Ola Electric", "Data Scientist", "2 years",
89
- "Built anomaly detection models for battery management. "
90
- "Developed Python ETL pipelines and SQL dashboards. "
91
- "First LLM experiment: GPT-3 for log summarisation."),
92
- ]),
93
- },
94
- {
95
- "id": "AI-003",
96
- "name": "Ananya Patel",
97
- "engineer_type": "AI Engineer",
98
- "current_position": "Principal AI Engineer",
99
- "current_title": "Principal AI Engineer",
100
- "parsed_metadata_calculated_years_experience": 7.0,
101
- "parsed_metadata_most_recent_company": "Microsoft India",
102
- "gen_ai_experience": "2+ years",
103
- "is_actively_or_passively_looking": False,
104
- "notice_period": "60 days",
105
- "parsed_skills": (
106
- "Python (Expert), LangChain (Expert), LangGraph (Advanced), "
107
- "RAG (Expert), Vector Databases (Expert), LLM fine-tuning (Advanced), "
108
- "Azure OpenAI (Expert), HuggingFace (Advanced), FastAPI (Advanced), "
109
- "Kubernetes (Core), MLflow (Core)"
110
- ),
111
- "parsed_summary": (
112
- "Principal AI Engineer at Microsoft with 7 years in ML/AI. "
113
- "Architect of Azure OpenAI enterprise integrations. "
114
- "Expert in multi-agent LangGraph systems and production RAG."
115
- ),
116
- "parsed_work_experience": ", ".join([
117
- we("Microsoft India", "Principal AI Engineer", "3 years",
118
- "Architected enterprise RAG systems using Azure OpenAI and Cognitive Search. "
119
- "Built multi-agent LangGraph workflows for document processing. "
120
- "Led team of 8 engineers. LLM fine-tuning on proprietary datasets. "
121
- "Pinecone and Weaviate for vector search at scale."),
122
- we("Samsung Research", "Senior ML Engineer", "2.5 years",
123
- "Built on-device NLP models using HuggingFace and PyTorch. "
124
- "Generative AI for Bixby voice assistant. "
125
- "Fine-tuned LLaMA models for multilingual tasks."),
126
- we("Mu Sigma", "ML Engineer", "1.5 years",
127
- "Statistical ML models for retail analytics. Python, scikit-learn, FastAPI."),
128
- ]),
129
- },
130
- {
131
- "id": "AI-004",
132
- "name": "Sneha Iyer",
133
- "engineer_type": "AI Engineer",
134
- "current_position": "ML Engineer",
135
- "current_title": "ML Engineer",
136
- "parsed_metadata_calculated_years_experience": 3.5,
137
- "parsed_metadata_most_recent_company": "Freshworks",
138
- "gen_ai_experience": "6 months - 1 year",
139
- "is_actively_or_passively_looking": True,
140
- "notice_period": "30 days",
141
- "parsed_skills": (
142
- "Python (Core), scikit-learn (Advanced), FastAPI (Basic), "
143
- "LangChain (Basic), OpenAI API (Basic), "
144
- "SQL (Core), pandas (Core), Docker (Basic)"
145
- ),
146
- "parsed_summary": (
147
- "ML Engineer at Freshworks. Recently started exploring LLMs and GenAI. "
148
- "Strong classical ML background, transitioning to GenAI workloads."
149
- ),
150
- "parsed_work_experience": ", ".join([
151
- we("Freshworks", "ML Engineer", "2 years",
152
- "Built NLP models for customer sentiment analysis using scikit-learn. "
153
- "Developed FastAPI endpoints for ML inference. "
154
- "Started exploring LangChain for RAG-based knowledge base. "
155
- "Used OpenAI API for text classification experiments."),
156
- we("Tata Consultancy Services", "Software Engineer", "1.5 years",
157
- "Developed Python data pipelines. SQL reporting. Some ML model training."),
158
- ]),
159
- },
160
- {
161
- "id": "AI-005",
162
- "name": "Vikram Nair",
163
- "engineer_type": "AI Engineer",
164
- "current_position": "Software Engineer",
165
- "current_title": "Software Engineer",
166
- "parsed_metadata_calculated_years_experience": 2.5,
167
- "parsed_metadata_most_recent_company": "Wipro",
168
- "gen_ai_experience": "only internship/project experience",
169
- "is_actively_or_passively_looking": True,
170
- "notice_period": "15 days",
171
- "parsed_skills": (
172
- "Python (Basic), scikit-learn (Basic), TensorFlow (Basic), "
173
- "pandas (Core), SQL (Core), REST APIs (Basic)"
174
- ),
175
- "parsed_summary": (
176
- "Software Engineer pivoting to AI/ML. "
177
- "Completed LLM project during internship. "
178
- "Eager to grow in GenAI space."
179
- ),
180
- "parsed_work_experience": ", ".join([
181
- we("Wipro", "Software Engineer", "2.5 years",
182
- "Backend Java development. REST APIs. Some Python scripting for data tasks. "
183
- "Built a small text classifier using scikit-learn as a side project."),
184
- ]),
185
- },
186
- {
187
- "id": "AI-006",
188
- "name": "Divya Krishnan",
189
- "engineer_type": "AI Engineer",
190
- "current_position": "Research Engineer",
191
- "current_title": "AI Research Engineer",
192
- "parsed_metadata_calculated_years_experience": 4.5,
193
- "parsed_metadata_most_recent_company": "IIT Bangalore AI Lab",
194
- "gen_ai_experience": "2+ years",
195
- "is_actively_or_passively_looking": True,
196
- "notice_period": "30 days",
197
- "parsed_skills": (
198
- "Python (Expert), PyTorch (Expert), HuggingFace Transformers (Expert), "
199
- "LLM fine-tuning (Advanced), RLHF (Core), "
200
- "FAISS (Advanced), LangChain (Core), FastAPI (Core), "
201
- "CUDA (Basic), MLflow (Core)"
202
- ),
203
- "parsed_summary": (
204
- "Research Engineer specializing in LLM fine-tuning and RLHF. "
205
- "Published 2 papers on instruction-tuned models. "
206
- "Strong PyTorch and HuggingFace expertise."
207
- ),
208
- "parsed_work_experience": ", ".join([
209
- we("IIT Bangalore AI Lab", "Research Engineer", "2 years",
210
- "Fine-tuned LLaMA 2 and Mistral models using RLHF and LoRA. "
211
- "Built RAG evaluation benchmarks using FAISS and LangChain. "
212
- "Published research on hallucination mitigation in LLMs. "
213
- "Generative AI for code generation tasks."),
214
- we("Anthropic (Intern)", "AI Safety Research Intern", "6 months",
215
- "Red-teaming Claude models. Prompt injection research. Constitutional AI experiments."),
216
- we("Samsung Research", "ML Engineer", "2 years",
217
- "On-device transformer models with HuggingFace. MLflow for experiment tracking. "
218
- "FastAPI for model serving. RAG prototype using FAISS."),
219
- ]),
220
- },
221
- {
222
- "id": "AI-007",
223
- "name": "Arjun Bose",
224
- "engineer_type": "AI Engineer",
225
- "current_position": "Data Scientist",
226
- "current_title": "Senior Data Scientist",
227
- "parsed_metadata_calculated_years_experience": 6.0,
228
- "parsed_metadata_most_recent_company": "Paytm",
229
- "gen_ai_experience": "1 to 1.5 years",
230
- "is_actively_or_passively_looking": False,
231
- "notice_period": "90 days",
232
- "parsed_skills": (
233
- "Python (Expert), XGBoost (Expert), TensorFlow (Core), "
234
- "SQL (Expert), Spark (Core), AWS (Core), "
235
- "OpenAI API (Basic), LangChain (Basic)"
236
- ),
237
- "parsed_summary": (
238
- "Senior Data Scientist at Paytm with strong classical ML background. "
239
- "Recently began integrating LLMs into fraud detection pipeline. "
240
- "More DS than AI Engineer profile."
241
- ),
242
- "parsed_work_experience": ", ".join([
243
- we("Paytm", "Senior Data Scientist", "3 years",
244
- "Built fraud detection models with XGBoost. A/B testing frameworks. "
245
- "Recently added LLM-based transaction explanation using OpenAI API. "
246
- "LangChain for internal audit Q&A chatbot."),
247
- we("HDFC Bank", "Data Analyst", "3 years",
248
- "SQL reporting and Python data pipelines. Credit risk models."),
249
- ]),
250
- },
251
- # ── Backend Engineers ─────────────────────────────────────────────────────
252
- {
253
- "id": "BE-001",
254
- "name": "Kiran Kumar",
255
- "engineer_type": "Backend Engineer",
256
- "current_position": "Senior Backend Engineer",
257
- "current_title": "Senior Backend Engineer",
258
- "parsed_metadata_calculated_years_experience": 6.0,
259
- "parsed_metadata_most_recent_company": "Razorpay",
260
- "gen_ai_experience": "i do not have gen ai experience",
261
- "is_actively_or_passively_looking": True,
262
- "notice_period": "30 days",
263
- "parsed_skills": (
264
- "Node.js (Expert), Express.js (Expert), AWS (Advanced), "
265
- "PostgreSQL (Advanced), Redis (Advanced), "
266
- "Microservices (Advanced), Docker (Advanced), "
267
- "Kubernetes (Core), REST APIs (Expert), GraphQL (Core)"
268
- ),
269
- "parsed_summary": (
270
- "Senior Backend Engineer at Razorpay. 6 years building high-throughput "
271
- "payment APIs. Expert in Node.js microservices on AWS."
272
- ),
273
- "parsed_work_experience": ", ".join([
274
- we("Razorpay", "Senior Backend Engineer", "3 years",
275
- "Led backend for payment gateway handling 50K TPS. Node.js microservices on AWS ECS. "
276
- "PostgreSQL + Redis for transaction state. Built GraphQL API layer. "
277
- "Kafka for event streaming between services."),
278
- we("PhonePe", "Backend Engineer", "2 years",
279
- "Node.js Express APIs for UPI payment flows. "
280
- "Redis caching for session management. PostgreSQL sharding. Docker deployment."),
281
- we("Cognizant", "Software Engineer", "1 year",
282
- "Java Spring Boot backend. REST API development. MySQL. Agile team."),
283
- ]),
284
- },
285
- {
286
- "id": "BE-002",
287
- "name": "Meera Joshi",
288
- "engineer_type": "Backend Engineer",
289
- "current_position": "Backend Engineer",
290
- "current_title": "Backend Engineer",
291
- "parsed_metadata_calculated_years_experience": 4.0,
292
- "parsed_metadata_most_recent_company": "Zomato",
293
- "gen_ai_experience": None,
294
- "is_actively_or_passively_looking": True,
295
- "notice_period": "45 days",
296
- "parsed_skills": (
297
- "Node.js (Advanced), Express.js (Advanced), MongoDB (Advanced), "
298
- "PostgreSQL (Core), Redis (Core), AWS (Core), "
299
- "Docker (Core), REST APIs (Advanced), Microservices (Core)"
300
- ),
301
- "parsed_summary": (
302
- "Backend Engineer at Zomato. Strong Node.js and Express expertise. "
303
- "Built food delivery order management APIs serving millions of users."
304
- ),
305
- "parsed_work_experience": ", ".join([
306
- we("Zomato", "Backend Engineer", "2.5 years",
307
- "Built order management microservices in Node.js/Express. "
308
- "MongoDB for order storage. Redis for caching menu data. "
309
- "AWS Lambda for async order events. REST APIs consumed by mobile apps."),
310
- we("MakeMyTrip", "Junior Backend Engineer", "1.5 years",
311
- "Node.js APIs for hotel booking. PostgreSQL. Docker containers."),
312
- ]),
313
- },
314
- {
315
- "id": "BE-003",
316
- "name": "Arjun Singh",
317
- "engineer_type": "Backend Engineer",
318
- "current_position": "Tech Lead",
319
- "current_title": "Backend Tech Lead",
320
- "parsed_metadata_calculated_years_experience": 8.0,
321
- "parsed_metadata_most_recent_company": "Zerodha",
322
- "gen_ai_experience": "i do not have gen ai experience",
323
- "is_actively_or_passively_looking": False,
324
- "notice_period": "90 days",
325
- "parsed_skills": (
326
- "Node.js (Expert), Express.js (Expert), AWS (Expert), "
327
- "PostgreSQL (Expert), DynamoDB (Advanced), Redis (Advanced), "
328
- "Microservices (Expert), Docker (Expert), Kubernetes (Advanced), "
329
- "REST APIs (Expert), System Design (Expert)"
330
- ),
331
- "parsed_summary": (
332
- "Tech Lead at Zerodha (India's largest stock broker). "
333
- "8 years of backend experience. Led architecture of trading platform "
334
- "backend serving 10M users."
335
- ),
336
- "parsed_work_experience": ", ".join([
337
- we("Zerodha", "Backend Tech Lead", "4 years",
338
- "Architected Node.js microservices for stock trading platform. "
339
- "AWS EKS for container orchestration. DynamoDB for order book. "
340
- "PostgreSQL for account management. Redis Cluster for real-time positions. "
341
- "Led team of 12 backend engineers."),
342
- we("CRED", "Senior Backend Engineer", "2.5 years",
343
- "High-performance REST APIs in Node.js/Express. AWS + Kubernetes deployment. "
344
- "PostgreSQL with read replicas. Redis caching."),
345
- we("Infosys", "Software Engineer", "1.5 years",
346
- "Java Spring Boot. REST APIs. MySQL. Agile development."),
347
- ]),
348
- },
349
- {
350
- "id": "BE-004",
351
- "name": "Kavya Reddy",
352
- "engineer_type": "Backend Engineer",
353
- "current_position": "Backend Engineer",
354
- "current_title": "Software Engineer - Backend",
355
- "parsed_metadata_calculated_years_experience": 3.0,
356
- "parsed_metadata_most_recent_company": "OYO Rooms",
357
- "gen_ai_experience": None,
358
- "is_actively_or_passively_looking": True,
359
- "notice_period": "30 days",
360
- "parsed_skills": (
361
- "Node.js (Core), Express.js (Advanced), MongoDB (Advanced), "
362
- "AWS (Basic), Docker (Basic), REST APIs (Advanced)"
363
- ),
364
- "parsed_summary": (
365
- "Backend Engineer at OYO with 3 years Node.js experience. "
366
- "Solid Express and MongoDB skills. Limited cloud exposure."
367
- ),
368
- "parsed_work_experience": ", ".join([
369
- we("OYO Rooms", "Backend Engineer", "2 years",
370
- "Node.js/Express APIs for hotel inventory management. "
371
- "MongoDB for property data. REST APIs for mobile apps. "
372
- "Basic AWS EC2 deployment."),
373
- we("Wipro", "Junior Developer", "1 year",
374
- "Python and Node.js scripting. REST API testing. QA tasks."),
375
- ]),
376
- },
377
- {
378
- "id": "BE-005",
379
- "name": "Dev Agarwal",
380
- "engineer_type": "Backend Engineer",
381
- "current_position": "Junior Backend Developer",
382
- "current_title": "Backend Developer",
383
- "parsed_metadata_calculated_years_experience": 1.5,
384
- "parsed_metadata_most_recent_company": "Startup XYZ",
385
- "gen_ai_experience": None,
386
- "is_actively_or_passively_looking": True,
387
- "notice_period": "15 days",
388
- "parsed_skills": (
389
- "Node.js (Basic), Express.js (Basic), MongoDB (Basic), "
390
- "REST APIs (Basic), JavaScript (Core)"
391
- ),
392
- "parsed_summary": (
393
- "Junior backend developer with 1.5 years experience. "
394
- "Learning Node.js and Express. Early in career."
395
- ),
396
- "parsed_work_experience": ", ".join([
397
- we("Startup XYZ", "Junior Backend Developer", "1.5 years",
398
- "Node.js Express REST APIs for e-commerce app. MongoDB CRUD operations. "
399
- "Basic deployment on Heroku."),
400
- ]),
401
- },
402
- # ── Edge Cases ────────────────────────────────────────────────────────────
403
- {
404
- "id": "EDGE-001",
405
- "name": "Rohan Verma",
406
- "engineer_type": "AI Engineer",
407
- "current_position": "Fresh Graduate",
408
- "current_title": None,
409
- "parsed_metadata_calculated_years_experience": None, # years_unknown
410
- "parsed_metadata_most_recent_company": None,
411
- "gen_ai_experience": "only internship/project experience",
412
- "is_actively_or_passively_looking": True,
413
- "notice_period": "Immediate",
414
- "parsed_skills": (
415
- "Python (Basic), TensorFlow (Basic), scikit-learn (Basic), "
416
- "LangChain (Basic), SQL (Basic)"
417
- ),
418
- "parsed_summary": (
419
- "Recent CS graduate. Built a RAG chatbot as final year project using LangChain. "
420
- "Eager to start career in AI Engineering."
421
- ),
422
- "parsed_work_experience": ", ".join([
423
- we("University Project", "AI Intern", "6 months",
424
- "Built RAG-based document Q&A using LangChain and FAISS. "
425
- "Experimented with LLM prompt engineering. Python, FastAPI for serving."),
426
- ]),
427
- },
428
- {
429
- "id": "EDGE-002",
430
- "name": "Pooja Gupta",
431
- "engineer_type": "Frontend Engineer", # wrong type for AI JD
432
- "current_position": "Frontend Developer",
433
- "current_title": "React Developer",
434
- "parsed_metadata_calculated_years_experience": 4.0,
435
- "parsed_metadata_most_recent_company": "Accenture",
436
- "gen_ai_experience": "i do not have gen ai experience",
437
- "is_actively_or_passively_looking": False,
438
- "notice_period": "30 days",
439
- "parsed_skills": (
440
- "React (Expert), JavaScript (Expert), TypeScript (Advanced), "
441
- "Next.js (Advanced), CSS (Expert), REST APIs (Core)"
442
- ),
443
- "parsed_summary": (
444
- "Senior Frontend Developer specializing in React and Next.js. "
445
- "No backend or AI experience."
446
- ),
447
- "parsed_work_experience": ", ".join([
448
- we("Accenture", "Frontend Developer", "4 years",
449
- "React and Next.js UI development. TypeScript. REST API integration. CSS animations."),
450
- ]),
451
- },
452
- {
453
- "id": "EDGE-003",
454
- "name": "Siddharth Rao",
455
- "engineer_type": "AI Engineer",
456
- "current_position": "AI Engineer",
457
- "current_title": "AI Engineer",
458
- "parsed_metadata_calculated_years_experience": 3.0,
459
- "parsed_metadata_most_recent_company": "TCS",
460
- "gen_ai_experience": "2+ years", # claims 2+ years but work history won't support it
461
- "is_actively_or_passively_looking": True,
462
- "notice_period": "60 days",
463
- "parsed_skills": (
464
- "Python (Core), SQL (Core), pandas (Core), "
465
- "Excel (Advanced), PowerPoint (Advanced)"
466
- ),
467
- "parsed_summary": (
468
- "AI Engineer at TCS with self-reported 2+ years GenAI experience. "
469
- "Work history reveals primarily data analyst tasks, not AI engineering."
470
- ),
471
- "parsed_work_experience": ", ".join([
472
- we("TCS", "Business Analyst", "3 years",
473
- "Data analysis using SQL and Excel. PowerPoint presentations for clients. "
474
- "Python scripting for data cleanup. No LLM or ML model work."),
475
- ]),
476
- },
477
- ]
478
-
479
-
480
- def build_workbook():
481
- wb = openpyxl.Workbook()
482
- ws = wb.active
483
- ws.title = "Candidates"
484
-
485
- headers = [
486
- "id", "name", "engineer_type", "current_position", "current_title",
487
- "parsed_metadata_calculated_years_experience",
488
- "parsed_metadata_most_recent_company",
489
- "gen_ai_experience", "is_actively_or_passively_looking", "notice_period",
490
- "parsed_skills", "parsed_summary", "parsed_work_experience",
491
- ]
492
-
493
- # Header row styling
494
- header_fill = PatternFill("solid", fgColor="1F4E79")
495
- header_font = Font(bold=True, color="FFFFFF", size=11)
496
- for col_idx, header in enumerate(headers, start=1):
497
- cell = ws.cell(row=1, column=col_idx, value=header)
498
- cell.fill = header_fill
499
- cell.font = header_font
500
- cell.alignment = Alignment(horizontal="center", vertical="center")
501
-
502
- # Data rows
503
- row_fill_a = PatternFill("solid", fgColor="EBF3FB")
504
- row_fill_b = PatternFill("solid", fgColor="FFFFFF")
505
- wrap = Alignment(wrap_text=True, vertical="top")
506
-
507
- for row_idx, cand in enumerate(CANDIDATES, start=2):
508
- fill = row_fill_a if row_idx % 2 == 0 else row_fill_b
509
- values = [
510
- cand.get("id"),
511
- cand.get("name"),
512
- cand.get("engineer_type"),
513
- cand.get("current_position"),
514
- cand.get("current_title"),
515
- cand.get("parsed_metadata_calculated_years_experience"),
516
- cand.get("parsed_metadata_most_recent_company"),
517
- cand.get("gen_ai_experience"),
518
- cand.get("is_actively_or_passively_looking"),
519
- cand.get("notice_period"),
520
- cand.get("parsed_skills"),
521
- cand.get("parsed_summary"),
522
- cand.get("parsed_work_experience"),
523
- ]
524
- for col_idx, value in enumerate(values, start=1):
525
- cell = ws.cell(row=row_idx, column=col_idx, value=value)
526
- cell.fill = fill
527
- cell.alignment = wrap
528
-
529
- # Column widths
530
- widths = [12, 20, 18, 22, 22, 10, 22, 20, 10, 12, 60, 50, 120]
531
- for col_idx, width in enumerate(widths, start=1):
532
- ws.column_dimensions[ws.cell(row=1, column=col_idx).column_letter].width = width
533
-
534
- ws.row_dimensions[1].height = 20
535
- ws.freeze_panes = "A2"
536
-
537
- return wb
538
-
539
-
540
- if __name__ == "__main__":
541
- out_path = Path(__file__).parent / "sample_candidates.xlsx"
542
- wb = build_workbook()
543
- wb.save(out_path)
544
- print(f"Generated: {out_path}")
545
- print(f"Total candidates: {len(CANDIDATES)}")
546
- types = {}
547
- for c in CANDIDATES:
548
- t = c["engineer_type"]
549
- types[t] = types.get(t, 0) + 1
550
- for t, n in types.items():
551
- print(f" {t}: {n}")
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
sample_data/sample_job_description.md DELETED
@@ -1,68 +0,0 @@
1
- # Sample Job Description β€” AI Engineer (Used for Testing)
2
-
3
- This file represents the kind of JD the system is designed to parse.
4
- To test the system, convert this to a PDF and upload it via the UI.
5
-
6
- ---
7
-
8
- ## Job Title: AI Engineer
9
-
10
- **Company:** Wissen Technology
11
- **Location:** Bangalore, India (Hybrid)
12
- **Experience Required:** 3+ years
13
-
14
- ---
15
-
16
- ## About the Role
17
-
18
- We are looking for a skilled AI Engineer to join our growing AI/ML team.
19
- You will design, build, and deploy production-grade AI systems β€” including
20
- LLM pipelines, RAG architectures, and real-time inference services.
21
-
22
- ---
23
-
24
- ## Responsibilities
25
-
26
- - Design and implement RAG (Retrieval-Augmented Generation) pipelines for enterprise clients
27
- - Fine-tune and evaluate large language models (GPT-4, Claude, LLaMA)
28
- - Build vector search systems using FAISS, Pinecone, or Weaviate
29
- - Develop and maintain ML model serving infrastructure (FastAPI, Triton)
30
- - Collaborate with backend teams to integrate AI APIs into production systems
31
- - Write clean, tested, production-ready Python code
32
- - Mentor junior team members and conduct code reviews
33
-
34
- ---
35
-
36
- ## Required Skills
37
-
38
- - Python (Core) β€” 3+ years, production experience
39
- - LLM / Large Language Models β€” experience with GPT, Claude, or Gemini APIs
40
- - RAG (Retrieval-Augmented Generation) β€” pipeline design and evaluation
41
- - LangChain or LangGraph β€” agent and chain orchestration
42
- - Vector Databases β€” Pinecone, Weaviate, FAISS, or Chroma
43
- - FastAPI β€” building and deploying inference APIs
44
- - Machine Learning β€” model training, evaluation, deployment
45
-
46
- ## Preferred Skills
47
-
48
- - PyTorch β€” deep learning model training
49
- - HuggingFace Transformers β€” model loading, fine-tuning
50
- - Docker β€” containerized deployment
51
- - AWS or GCP β€” cloud deployment, SageMaker, Vertex AI
52
- - MLflow or W&B β€” experiment tracking
53
-
54
- ---
55
-
56
- ## GenAI Experience
57
-
58
- Minimum 1 year of hands-on GenAI experience required.
59
- Candidates with "2+ years" of production GenAI work preferred.
60
-
61
- ---
62
-
63
- ## What We Offer
64
-
65
- - Competitive salary + ESOP
66
- - Work on cutting-edge AI projects
67
- - Hybrid work model
68
- - Learning budget for certifications and conferences