Frontend to founding,
one era at a time.
I move fast across domains. Each role pulled me into a new part of the stack — voice AI, then healthcare AI — and each time I owned more of the product. Here's how I got here, and why I'm built for whatever's next.
I started as a frontend engineer and grew into the full stack — backend, cloud, AI pipelines, and RPA automation. At Diagna AI I owned FAXFlo end-to-end: 110+ React components, a 40-endpoint Node.js API, a distributed AWS document pipeline processing 1,000+ faxes daily, and the AI + voice automation that took the product live in a paying US clinic. I learn by building, prefer shipping over endless tutorials, and enjoy taking ownership beyond traditional frontend boundaries.
Took FAXFlo from a company pivot to its first paying US clinic in production. Owned the entire stack — React frontend, Node.js backend, AWS cloud pipeline, multi-model AI, Voice-AI scheduling, RPA automation, and analytics.
- ▹Full-stack owner: shipped the React 19 frontend solo (110+ components, lazy-loaded routes, per-clinic feature flags, ~60% bundle reduction) AND the production backend (Node.js · Express · PostgreSQL, 40+ REST endpoints, JWT/RBAC auth, Redis-backed BullMQ queues, Swagger docs).
- ▹Architected a distributed AWS pipeline (S3 · SQS · Textract · SNS · Bedrock) processing 1,000+ medical documents daily at 99%+ uptime, with DLQ handling and Slack alerting.
- ▹Integrated Claude (Sonnet), GPT-4o, and AWS Bedrock for document classification at ~95% accuracy across 40+ categories — extracting structured patient data with custom prompts and retry logic.
- ▹Built an AI SMS orchestrator (Twilio · Telnyx · Vonage) for opt-in/opt-out flows, appointment reminders, and follow-up — and a Voice-AI scheduling module (VAPI + ElevenLabs) cutting manual outreach ~70%.
- ▹Engineered an RPA automation suite (Robocorp · Python · FastAPI · Redis RQ) for MDLand EHR — OTP/2FA login, patient search, document upload, and schedule sync via iframe-heavy UI, with a React Chrome Extension for on-page orchestration.
- ▹Built the HIPAA-compliant PostHog analytics dashboard (EMR sync counts, bar charts, appointment analytics) and the investor + clinic demo that closed the first paying US clinic.
- ▹Wrote a custom Zustand + Immer document-editing engine with field-level diffing and patch-only updates; PDF.js rendering at 300 DPI with multi-page batch processing and ~80% image compression.
The only frontend engineer on VoiceGenie, a generative-AI voice sales platform. Built the dashboard and marketing site that closed the first enterprise customers.
- ▹Grew VoiceGenie from 0 to $10K MRR in 11 months as the sole frontend engineer.
- ▹Built a live variable composer for AI voice scripts — drop @name / @appointment tokens that resolve per-contact at call time.
- ▹Integrated HubSpot, ElevenLabs, GoHighLevel, and Cal.com into one workflow.
- ▹Cut page load times 30–50% with code splitting, lazy loading, and targeted caching.
Frontend, full-stack, AI — open to everything.
I've shipped in the voice-AI era and the healthcare-AI era. I learn by building, take ownership beyond traditional boundaries, and I'm looking for the next hard problem to own end-to-end.