Projects
Things I’ve built, with the tradeoffs visible.
A selection of applied AI, backend, data, and tooling work. I keep the architecture, constraints, failure modes, and implementation details close to the work itself.
Selected work
Current engineering focus
FreightSense: 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.
Earlier work
Data, analysis, and tooling
Older projects that still show useful parts of how I approach parsing, analysis, and software tooling.
AmbitionBox salary scraper: from embedded page data to usable records
A Python salary-data pipeline with a custom Nuxt payload parser, HTML fallback, batch collection and pandas-based cleaning.
EvidenceCustom parser for embedded Nuxt payloads, an HTML fallback path, batch collection and pandas-based cleaning.
Reading 75,000+ consumer complaints in Power BI
A Power BI portfolio project exploring complaint volume, response timeliness and disputes across products, regions and time.
Evidence75,000+ complaint records explored across product, geography, response timeliness and disputes in Power BI.