• Architect and build scalable multi-agent systems • Own backend services, APIs, and data pipelines • Collaborate with Product, Design, and Client teams • Continuously improve existing architecture and reduce operational complexity

• 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.

• Provide technical leadership for the AI Tools development unit, defining coding standards, architecture, quality, and security • Conduct code reviews, pair programming, and mentor mid-level and junior developers to raise the team's technical level • Participate in product planning with stakeholders, translating business requirements into viable, prioritized technical solutions • Define and evolve the unit's technical roadmap, including decisions on stack, infrastructure, integrations, and technical debt • Establish and track engineering metrics (lead time, quality, performance, availability) and SLOs for the products under your responsibility • Design and develop full stack applications using Python (FastAPI/Flask) on the backend and React/TypeScript on the frontend • Architect and build robust, scalable, secure, and well-documented RESTful APIs (OpenAPI/Swagger) • Model and optimize relational databases, especially PostgreSQL, including schema design, complex queries, indexes, and performance tuning • Make architecture decisions focused on microservices, event-driven architecture, and horizontal scalability • Build modern, accessible, high-performance interfaces using Vite, Zod, Tailwind, and Mantine, with state management via Zustand, Context API or Recoil

Role Description 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 - Document understanding pipelines that turn unstructured clinical data into usable signal This is a hands-on, high-ownership role for an engineer who wants to do work with direct patient impact. What you'll do - 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. - 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. - 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. - Operationalize models trained by the AI Scientist team: serving, evaluation in production, rollback paths, and feedback loops that turn real usage into training and eval data. - Partner with clinicians, the data engineering team, and research collaborators to translate clinical requirements into specifications and deliverable systems. - Educate and mentor PMs and engineers across Atria on applied AI best practices. Leadership and Influence - Set technical direction for AI engineering at Atria: architecture decisions, build-vs-buy calls, and evaluation and observability standards. - Raise the bar on engineering practices, code review, observability, and incident response. - 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. - A bias to ship: prefer a rough thing in production tomorrow over a beautiful thing in a design doc next quarter. - A scrappy streak: pick up an unfamiliar tool, framework, or clinical concept quickly. - A serious drive to keep getting better: read others' code, papers, and post-mortems. Qualifications - 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. - 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. - Familiarity with safety considerations for LLM applications. - Practical understanding of HIPAA, BAAs, PHI handling, and working in a regulated environment. - Strong written communication: design docs, technical RFCs, and documentation. Nice to have - Experience in healthcare, clinical informatics, or other regulated domains. - Familiarity with medical ontologies (LOINC, SNOMED CT, ICD-10, RxNorm) and clinical data standards (FHIR, HL7). - Experience with self-hosted model serving and inference optimization. - Multimodal experience: vision, structured data, or time-series data alongside text. Salary and Benefits - Salary range: $190,000 - $250,000 + performance-based bonus - 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 - 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