Senior AI Engineer

Atria Health and Research Institute

6d • $190,000 - $250,000

About The Position

As a Senior AI Engineer at Atria, you will own the design, development, and production deployment of the LLM-powered systems that put AI directly in front of clinicians and members: agentic medical companions, clinical decision support, and the document understanding pipelines that turn unstructured clinical data into usable signal. You'll work end-to-end across orchestration, retrieval, evaluation, and deployment, building on a data estate that very few organizations in the world can match (whole-genome sequencing, advanced imaging, longitudinal labs and wearables, multi-generational family records) and translating clinical and operational requirements into AI products that are reliable, safe, observable, and (crucially) actually used. This is a hands-on, high-ownership role for an engineer who wants to do work with direct patient impact, and for whom "we'll add evals later" is the sort of phrase that ruins a perfectly good Tuesday.

Requirements

• Hands-on experience building and operating LLM-powered or production ML systems: 4+ years.
• Strong Python skills and deep familiarity with at least one production backend framework (FastAPI, Flask, etc.).
• Hands-on experience with LLM orchestration, function/tool calling, and retrieval system design: chunking, hybrid search, reranking, and the rest of the unfashionable middle bit that makes RAG actually work.
• Working knowledge of a cloud data warehouse (Snowflake strongly preferred) and modern data tooling such as dbt, Dagster, or Airflow.
• A track record of designing evaluation systems for LLM applications — including the ones that caught regressions before users did, and the ones that didn't.
• Familiarity with safety considerations for LLM applications: guardrails, adversarial testing, and the failure modes that tend to introduce themselves at 4pm on a Friday.
• Practical understanding of HIPAA, BAAs, PHI handling, and the everyday realities of working in a regulated environment without losing the will to live.
• Strong written communication: design docs, technical RFCs, and documentation that someone else can actually follow six months later.

Nice To Haves

• Experience in healthcare, clinical informatics, or other regulated domains (finance, biotech, anywhere people will sue you for being sloppy).
• Familiarity with medical ontologies (LOINC, SNOMED CT, ICD-10, RxNorm) and clinical data standards (FHIR, HL7).
• Experience with self-hosted model serving (vLLM, Triton, TGI, SGLang) and inference optimization.
• Multimodal experience: vision, structured data, or time-series data alongside text.

Responsibilities

• Architect and ship production AI systems end-to-end (orchestration, retrieval, inference, evaluation, and monitoring) for clinical decision support, document understanding, and agentic medical companions.
• Design agentic workflows with custom skills and harnesses, using frontier LLMs and self-hosted models where appropriate, and resisting the urge to reach for an agent when a function call would do.
• Lead development of structured information extraction pipelines from clinical documents, including automated verification systems and human-in-the-loop gates, where necessary.
• Build robust evaluation infrastructure (golden datasets, LLM-as-judge, regression tests, online A/B evaluation) that gates every model and prompt change. Accuracy, safety, cost, and latency are first-class metrics.
• Engineer for latency and cost: streaming, caching, prompt compression, model routing, and inference-cost budgets.
• Own production health: trace- and span-level observability, prompt versioning, drift detection, cost monitoring, replay-from-production for debugging, PHI-safe logging throughout, and the general art of finding out something is broken before a clinician does.
• Operationalize models trained by the AI Scientist team: serving, evaluation in production, rollback paths, and the feedback loops that turn real usage into training and eval data, rather than into a Slack thread nobody reads.
• Partner with clinicians, the data engineering team, and our research collaborators to translate clinical requirements into specifications and deliverable systems.
• Educate and mentor PMs and engineers across Atria on applied AI best practices, from prompt and evaluation design to choosing the right model for the job (which, surprisingly often, is not the largest one).
• Set technical direction for AI engineering at Atria: architecture decisions, build-vs-buy calls, and the evaluation and observability standards the team actually works to.
• Raise the bar on engineering practices, code review, observability, and incident response. Quietly, persistently, and with grace.
• Drive vendor and partner technical due diligence for AI/ML vendors: BAA scope, PHI handling, sub-processor obligations, and IP terms.
• Mentor other AI engineers through code review, design docs, and architecture decisions, with the patient conviction that good systems are made twice: once badly, then properly.

Benefits

• Excellent health and wellness benefits, fully covered by Atria, effective date of hire
• OneMedical membership for employees & dependents, giving access to 24/7 virtual care
• Fertility & family planning
• Company-covered preventive health screenings through partner hospitals (calcium score)
• Fitness Perks, including Wellhub +
• 401k contributions and 4% match starting after 6 months
• Flexible Time Off
• Continuing medical education (CME) and CEU support for professional licensure

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed