Fullstack Architect

About The Project (description, Duration, Stage) The client is the largest US network of in-home veterinary hospice and end-of-life care. A major US private-equity sponsor drives the AI program and plans more projects across its portfolio. We built a real-time voice copilot for their Veterinary Care Coordinators (VCCs). The copilot listens to live calls with pet families. It extracts appointment and clinical fields while the call runs. It fills the client's scheduling system through a Chrome extension. A second workstream, the Vet Visit Copilot , sends each vet an AI pre-visit briefing by email (Amazon SES). Next is the production phase . Stage: production SOW in executive alignment; start expected September 2026. ramp toward 1.0 FTE as production scales. He stays at 0.15–0.2 FTE for supervision and knowledge transfer during ramp-up, so the new architect gets a structured handover. Own the technical architecture and delivery of the voice copilot from validated PoC to production Hit the bar this client tests against: latency, accuracy, concurrency, and cost Keep expectations aligned: production polish is in scope now; Technical architecture & hands-on implementation Own the full pipeline: streaming speech-to-text, LLM field extraction, Chrome-extension delivery, and AWS infrastructure Drive latency work: cut P95 from ~6s toward ~2s; remove post-processing corner cases (occasional ~1min lag on one field type) Run model A/B tests (current pair: Claude Haiku vs GPT Luna) with golden-set evaluation for phonetic name and email accuracy Own evaluation and cost: 5–10+ concurrent calls, strict data isolation between users, monitoring, alerting, and safe rollback Ship epics end to end (example: the SES email briefing service); VCCs test edge cases and expect production quality Present concrete system behavior, with numbers — this account rewards evidence, not slides all client-facing materials pass ADM review before sending Lead the AI Engineer and the pod: set tasks, review output, unblock fast Absorb the handover from the outgoing architect (0.15–0.2 FTE supervision window) and become independent fast the project must have no single point of failure Real-time voice pipelines: streaming STT, turn handling, low-latency LLM inference — hands-on LLM engineering: prompt engineering, structured extraction, guardrails, model A/B evaluation AWS: Bedrock, serverless patterns, SES; Full-stack pragmatism: strong Python; enough TypeScript / Chrome-extension knowledge to own the integration Clear spoken and written English for demanding US executives Contact-center / agent-assist patterns and metrics (handle time, cost per call, concurrency) Production LLM operations: load testing, data isolation, incident handling Experience Voice AI in production — mandatory. Shipped at least one real-time voice or speech product to real users (agent assist, voice bot, live transcription copilot). 6+ years hands-on AI/ML engineering, with strong recent LLM production practice ~ Can show measured P95 reductions and concurrency fixes on a live system ~ Consulting / client-facing seniority. Calm and precise under detailed UAT scrutiny; manages expectations well US client experience with Eastern-time overlap #