Shivam Govind Rao
builds production AI — agents, voice, LLM pipelines — and the full stack around them.
AI Engineer with 2.5 years building production AI products end to end: LLM pipelines, multi-agent systems (LangGraph), RAG and real-time voice agents, plus the React, Node.js and Python systems around them. At Diagna AI I built the document-AI platform that processes 1,000+ medical faxes a day for live US clinics; before that I shipped VoiceGenie, a generative-AI voice platform, from 0 to $10K MRR in 11 months. I care about AI that holds up in production: guardrails in code, evals, and measured latency and cost.
Where I've shipped.
Two AI products, both taken to production and paying customers: document AI for US clinics, and a generative-AI voice platform.
Built the document-AI platform behind FAXFlo, taking it from a company pivot to live paying US clinics. Owned it end to end: multi-model LLM extraction on AWS Bedrock, the HIPAA-compliant backend and queues, RPA write-back into a legacy EHR, and both React frontends.
- ▹Led multi-model AI on AWS Bedrock (Claude Sonnet, Amazon Nova Pro, Llama) classifying and extracting 1,000+ medical faxes a day across 40+ document categories for live US clinics
- ▹LLM reliability: pre-flight token counting, cost-aware model routing, schema-validated JSON with retries, and a fallback chain across model families
- ▹Cut manual fax triage from about 3 hours to 10 minutes a day by chaining AI extraction, patient matching, human review and EHR write-back
- ▹HIPAA backend: 40+ endpoints, a 25-model Postgres schema, S3 · SQS · SNS into 7 BullMQ queues; a FastAPI RPA service took referrals from 4.2 days to same day
- ▹Built both production React 19 frontends, including the editor for reviewing AI output
Sole frontend engineer on VoiceGenie, a generative-AI voice agent platform, and a collaborator on its voice infrastructure. Built the product that took it to $10K MRR and closed the first enterprise customers.
- ▹Sole frontend engineer — designed and built the entire platform and marketing site from 0
- ▹Campaign builder, ElevenLabs voice tuning, and post-call analytics with AI entity extraction
- ▹Collaborated on Twilio voice-AI infrastructure for 2K+ concurrent calls, with rate limiting that blocked 15K+ abusive requests a day
- ▹Stripe payments end to end · CRM sync (HubSpot · GoHighLevel · Cal.com) · 0 → $10K MRR in 11 months
Things I built.
All projects →PayOps AI. An AI investigator that isn't allowed to touch the money.
Multi-agent payment reconciliation. When a company's gateway, orders, ledger, webhooks and settlement disagree, a LangGraph system of parallel specialists (Jev + Gemini) investigates, cites evidence and proposes a fix. Deterministic policy, four-eyes approvals, exactly-once execution and an independent validator decide what actually happens.
▶3-min narrated demo

