Spaces:
Running
Running
| <html lang="en"> | |
| <head> | |
| <meta charset="utf-8"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1"> | |
| <title>About Chandra Vikram</title> | |
| <style> | |
| :root{color-scheme:light;--ink:#182e32;--muted:#526469;--accent:#14665e;--line:#d9e2df} | |
| *{box-sizing:border-box}body{margin:0;background:#f5f7f4;color:var(--ink);font:16px/1.7 system-ui,-apple-system,sans-serif}main{max-width:980px;margin:auto;padding:64px 28px}header{padding-bottom:32px;border-bottom:1px solid var(--line)}.eyebrow{text-transform:uppercase;letter-spacing:.14em;font-size:12px;font-weight:700;color:var(--accent)}h1{font-size:clamp(36px,6vw,62px);line-height:1.1;letter-spacing:-.04em;margin:16px 0}h2{font-size:25px;letter-spacing:-.02em;margin:40px 0 18px}h3{font-size:17px;line-height:1.4;margin:0 0 8px}p{margin:0 0 16px}.lead{font-size:21px;max-width:760px}.muted{color:var(--muted)}nav{display:flex;gap:12px 24px;flex-wrap:wrap;margin-top:22px}a{color:var(--accent);text-underline-offset:4px}a:hover{text-decoration-thickness:2px}a:focus-visible{outline:3px solid var(--accent);outline-offset:4px}.grid{display:grid;grid-template-columns:repeat(2,minmax(0,1fr));gap:16px}.card{background:#fff;border:1px solid var(--line);border-radius:12px;padding:22px}.card p{color:var(--muted);font-size:15px;margin:0}.work{padding:20px 0;border-bottom:1px solid var(--line)}.work p{color:var(--muted);margin:8px 0 0}.note{background:#e7efeb;padding:20px 24px;border-radius:10px;margin-top:28px}footer{font-size:14px;color:var(--muted);margin-top:40px}@media(max-width:600px){main{padding:36px 20px}.grid{grid-template-columns:1fr}.lead{font-size:19px}} | |
| </style> | |
| </head> | |
| <body> | |
| <main> | |
| <header> | |
| <div class="eyebrow">Healthcare AI · Models, evidence, and connected care</div> | |
| <h1>Chandra Vikram Singh</h1> | |
| <p class="lead">I work on AI that can make sense of clinical information and fit into the systems people use to deliver care.</p> | |
| <p class="muted">Healthcare AI engineer · MS in Health Informatics, Indiana University · Background in pharmaceutical sciences</p> | |
| <nav aria-label="Find me online"> | |
| <a href="https://chandravikram.com/" target="_blank" rel="noopener noreferrer">Portfolio & research notes ↗</a> | |
| <a href="https://github.com/supermax01" target="_blank" rel="noopener noreferrer">GitHub ↗</a> | |
| <a href="https://x.com/thuggeshwar_" target="_blank" rel="noopener noreferrer">X / Twitter ↗</a> | |
| <a href="https://huggingface.co/Supermax01" target="_blank" rel="noopener noreferrer">Hugging Face ↗</a> | |
| </nav> | |
| </header> | |
| <section aria-labelledby="about"> | |
| <h2 id="about">About me</h2> | |
| <p>My route into AI began with pharmaceutical sciences and continued through graduate study in health informatics. That combination shapes the questions I bring to engineering: What information is missing? What evidence supports the answer? How will the result reach a patient or clinician?</p> | |
| <p>I work across clinical language models, retrieval, interoperability, and applications for patients and care teams. I’m especially interested in the connections between them: grounding a model in the right evidence, carrying context from the health record, and making its uncertainty visible to the people using it.</p> | |
| <p>Healthcare is my main focus, and I also explore broader applied AI. I value systems whose behavior can be inspected, tested, and improved.</p> | |
| </section> | |
| <section aria-labelledby="interests"> | |
| <h2 id="interests">What I’m exploring</h2> | |
| <div class="grid"> | |
| <article class="card"><h3>Clinical language & reasoning</h3><p>Medical question answering, clinical NLP, and reasoning across longitudinal patient records.</p></article> | |
| <article class="card"><h3>Retrieval & knowledge graphs</h3><p>Clinical RAG, guideline retrieval, patient context, and whether an answer’s citations actually support its claims.</p></article> | |
| <article class="card"><h3>Fine-tuning & alignment</h3><p>Adapting open language models for clinical tasks and evaluating what changes after training.</p></article> | |
| <article class="card"><h3>Interoperability</h3><p>HL7 FHIR, SMART on FHIR, and the infrastructure connecting AI applications with health records.</p></article> | |
| <article class="card"><h3>Agents, voice & telehealth</h3><p>Clinical workflows, conversational interfaces, and useful handoffs between AI systems and care teams.</p></article> | |
| <article class="card"><h3>Evaluation & safety</h3><p>Grounded benchmarks, privacy, uncertainty, failure analysis, and keeping clinicians involved.</p></article> | |
| </div> | |
| </section> | |
| <section aria-labelledby="work"> | |
| <h2 id="work">Selected work & notes</h2> | |
| <article class="work"><h3><a href="https://huggingface.co/Supermax01/qwen3-14b-tpn-finetuned" target="_blank" rel="noopener noreferrer">Qwen3 fine-tuning experiment ↗</a></h3><p>A public Qwen3 model adapted from Unsloth’s 4-bit Qwen3-14B checkpoint, trained with Unsloth and Hugging Face TRL.</p></article> | |
| <article class="work"><h3><a href="https://github.com/supermax01/Carepal" target="_blank" rel="noopener noreferrer">Carepal ↗</a></h3><p>A patient-facing healthcare application exploring AI assistance, patient-reported outcomes, and connections to clinical data systems.</p></article> | |
| <article class="work"><h3><a href="https://chandravikram.com/" target="_blank" rel="noopener noreferrer">Clinical AI working notebook ↗</a></h3><p>Project ideas and preliminary manuscripts spanning FHIR infrastructure, clinical benchmarks, voice agents, knowledge graphs, retrieval, and alignment.</p></article> | |
| <p class="note">The notebook describes work in progress. Project proposals, evaluation plans, and targets should be read in that context.</p> | |
| </section> | |
| <footer>Find project details and updates at <a href="https://chandravikram.com/" target="_blank" rel="noopener noreferrer">chandravikram.com</a>.</footer> | |
| </main> | |
| </body> | |
| </html> | |