Applied AI engineerPersonal site & notebook
Vedant Andhale.
I build reliable AI systems and write about the engineering behind them.
My work spans retrieval, agents, evaluation, backend systems, and the practical details that make software observable, testable, and useful.
Selected work
All projectsFreightSense: making shipment recommendations inspectable
A FastAPI decision-support prototype combining deterministic shipping calculations, LLM recommendations and a human override history.
Deterministic rules + LLM comparison, explicit disagreement handling, API fallbacks and append-only human overrides.
Crop Cure: a grape-leaf classifier inside WhatsApp
A research prototype connecting a PyTorch image classifier to a multilingual WhatsApp workflow with FastAPI.
WhatsApp → FastAPI → PyTorch inference, multilingual response flow and an explicit low-confidence fallback.
loadfile: one call to load tabular data
A small Python package that loads local and cloud files into pandas through a consistent API, replacing repeated file-loading code.
One API across local and cloud tabular data with fsspec backends, multiple file formats and ZIP member handling.
Latest writing
NotebookReturning to open source: collaboration first, code second
Why I am returning to open source in 2026, what I learned from EddieHub, and how I want to contribute differently as a working engineer.
First-Year Computer Science Roadmap: What I Wish I Knew
A practical first-year CS guide to DSA, AI, projects, placements, referrals, GATE, internships, and building strong software engineering fundamentals.
20 minKeep a static-site build easy to explain
The build contract behind this Hugo portfolio: pinned inputs, explicit environments and generated HTML.
2 minBefore caching a result, define when it is wrong
Cache keys, stale data and invalidation are part of the result contract, not just performance settings.
2 minWorking library
Things I want to find again
A framework for building applications with foundation models, including evaluation and deployment.
articleBackground tasks in FastAPIFor work that runs after sending a response, with guidance on when a separate worker system is more appropriate.
articleBuilding a generative AI platformChip Huyen on the components and decisions around a generative AI application.