Boston, MA · open to full-time
Full-Stack AI Engineer in Boston
Abhishek Sagar Sanda is a full-stack AI engineer who owns the model loop and the product surface - FastAPI backends, Next.js clients, voice telephony, and retrieval stacks that cite sources in production.
What a full-stack AI engineer ships
A full-stack AI engineer does not stop at a notebook. They design the API, the orchestration, the evaluation harness, and the UI or call path users actually hit - then keep latency, citations, and failover honest under load.
As a full-stack AI engineer, Abhishek builds across Python and TypeScript: voice agents on Twilio and LiveKit, RAG over large corpora with ChromaDB-style retrieval, and product surfaces that expose measurable behavior rather than slide-deck demos.
Proof across the stack
- BitVoice Pay - voice-first Lightning wallet end to end: telephony, agent loop, and live dial-in proof.
- Northeastern University Assistant - RAG over 80,000+ pages with citations, retrieval plus product surface.
- AutoAce (YC F25) - voice-agent OS for dealerships: latency cut 8.5s → 3.9s, backfilled sessions, three-layer LiveKit fence.
- AI Interview Coach IVR - multi-turn interview coaching on a live call path.
Hire a full-stack AI engineer
Based in Boston and available for full-time roles, Abhishek joins teams that need a full-stack AI engineer to take voice and retrieval products from prototype to dependable service. Related role pages: AI agent engineer, forward deployed engineer, ML platform engineer. See selected work, the resume, or book a call.