Sr AI Engineer

Our client is a venture-backed startup rebuilding how people access and experience healthcare — combining AI with real clinical expertise at the product level. Backed by top-tier investors, small team, moving fast.

Senior AI engineering role spanning model development, data infrastructure, retrieval systems and voice and video AI. You'll be close to the core product, involved in technical decisions from day one and expected to lead across the stack.

What You'll Work On

AI Agents and Product Intelligence Build and iterate on agent workflows handling multi-step reasoning, tool use and structured decision making. Design guardrails, fallback logic and escalation paths for safe autonomous behavior. Ship AI-powered features end to end from model selection to UX integration.

Knowledge Systems and Search Improve retrieval accuracy and data lineage tracking. Rebuild knowledge bases so citations resolve to original sources and searches are fast, relevant and prioritize high quality information.

Data Pipelines and Integrity Rebuild data pipelines to eliminate stale data and ensure full traceability. Design systems that sync cleanly with external data partners. Build and maintain curation pipelines that produce high quality training and evaluation datasets.

Voice and Video AI Build and optimize real-time voice pipelines — speech-to-text, natural language understanding, text-to-speech. Develop low-latency streaming voice agents with interruption handling, turn-taking logic and conversational state management. Fine-tune models for domain-specific terminology, diverse accents and accessibility needs.

Model Training and Fine-Tuning Fine-tune and adapt foundation models on domain-specific data. Design training pipelines including data curation, annotation workflows, hyperparameter tuning and model evaluation. Run experiments across prompt engineering, RLHF, distillation and other techniques. Build automated and human-in-the-loop evaluation frameworks to measure quality, safety and regression.

Observability and Production Reliability Instrument model performance in production — latency, token usage, output quality, drift. Build monitoring, tracing, logging and auditing infrastructure that maintains compliance-grade visibility without redundancy.

What You Bring

• Strong Python skills
• Experience building and owning production AI or ML systems
• Hands-on experience with LLM APIs, prompt engineering and shipping AI-powered features
• Experience with system refactors, schema migrations and data infrastructure
• Familiarity with PostgreSQL and AWS
• Comfort owning problems end to end across the full stack
• Seniority to lead technical direction and bring others along

Interested? Apply and I'll be in touch if there's a fit! We partner with a number of exciting clients across the industry, so even if this particular role isn't the perfect match, another opportunity might be just around the corner.