I design and ship reliable AI systems — retrieval, agents, evaluation, and the backend infrastructure around them.
I care about the parts that make model capability usable in production: data contracts, APIs, failure handling, observability, performance, and human review.
Selected work
A FastAPI decision-support prototype combining deterministic shipping calculations, LLM recommendations and a human override history.
Evidence: Deterministic rules + LLM comparison, explicit disagreement handling, API fallbacks and append-only human overrides.
A research prototype connecting a PyTorch image classifier to a multilingual WhatsApp workflow with FastAPI.
Evidence: WhatsApp → FastAPI → PyTorch inference, multilingual response flow and an explicit low-confidence fallback.
A small Python package that loads local and cloud files into pandas through a consistent API, replacing repeated file-loading code.
Evidence: One API across local and cloud tabular data with fsspec backends, multiple file formats and ZIP member handling.
Notebook
A practical first-year CS guide to DSA, AI, projects, placements, referrals, GATE, internships, and building strong software engineering fundamentals.
The build contract behind this Hugo portfolio: pinned inputs, explicit environments and generated HTML.
Cache keys, stale data and invalidation are part of the result contract, not just performance settings.
A practical approach to reproductions, hypotheses and boundary checks when stepping through the process is not available.