AI Engineer
I build AI systems that don't just answer —
they reason, retrieve, and act in production.
Multi-agent pipeline — SCOUT → CRITIC → PRESCRIBER — that audits product listings, detects revenue loss signals, and generates evidence-backed prescriptions. Orchestrated via Inngest, served on Next.js with demo mode gated by isDemo flag.
HIPAA-compliant clinical audio-to-record pipeline on GCP — converts physician audio into structured medical records using MedGemma. FastAPI backend deployed on Cloud Run with full IAM hardening.
6-stage financial ML pipeline: news ingestion → FinBERT sentiment → Z-score anomaly → GPT-4 alert summaries. JWT auth, watchlist API, React/TypeScript frontend.
6-layer agentic system — Planner / Executor / Synthesizer agents via LangGraph. ChromaDB RAG + Tavily web search. Built bottom-to-top in 13 days solo.
Production-quality Q&A bot with MongoDB Atlas vector storage, SentenceTransformers (384-dim), Azure OpenAI GPT-3.5 Turbo. 100% test accuracy, 69.2% avg token overlap.
I'm an AI Engineer and Tech Lead who's spent the last year shipping agentic systems across healthcare, fintech, and e-commerce — from solo hackathon builds to leading multi-person teams on production pipelines.
I care about systems that actually work: clean orchestration, schema discipline, test coverage, and agents that don't hallucinate off the rails. The gap between LLM demo and production system is where I operate.
Currently Tech Lead on the Revenue Recovery Engine at PM Accelerator — a multi-agent AI pipeline for e-commerce. Actively open to AI Engineer roles, remote preferred.
Open to full-time AI Engineer roles and interesting collaborations.