About the RoleOpenLoop is building the future of healthcare infrastructure. We are hiring for this role at the Senior, Staff and Senior Staff levels. Apply once; we will calibrate level during the process based on the scope you have carried and the depth you bring, not on years alone.
What You'll Do- Ship Production Agents: Build and run LLM-based agents and assistants that real users depend on, not prototypes.
- Agent Runtime & Orchestration: Build how agents run, call tools, hold context and hand off work, including failure handling, retries, timeouts and sandboxing.
- Evaluation: Build evaluation sets, test harnesses, regression tests and AI-graded evals so the team can show "this got better" with numbers and catch regressions before users do.
- Model Access & Operations: Work across multiple model providers, manage version upgrades and plan fallbacks for when a provider fails.
- Observability & Cost: Trace what agents did and why, monitor behavior in production, and attribute AI spend to each agent and use case.
- Grounding & Retrieval: Connect agents to real, messy company data through retrieval (RAG), context design and prompt engineering, so answers are based on facts.
- Workflow Design: Work with operations teams to decide which steps of a human workflow an agent can do reliably, and when it should escalate to a person.
- Security, Privacy & Safety: Keep patient data (PHI) protected in every AI system, control what agents can access, and defend against misuse such as prompt injection.
- Cloud & Data Foundations: Build on GCP and partner with the Data Platform teams who provide the governed data agents use.
- Raise the Bar: Contribute to code and design review, and help engineers who are newer to AI.
- Cross-functional Work: Explain AI trade-offs in plain language to product, operations and clinical stakeholders, including when the honest answer is "the AI isn't ready for this yet."
- Other duties as assigned.
Who You AreRequired Qualifications:- Bachelor's degree in Computer Science, Engineering, or a related technical field
- Proven Engineering Experience: 5 to 15+ years of software engineering experience.
- Production LLM Experience: Hands-on experience building and running LLM-based systems in production that real users relied on, not only demos, prototypes or personal projects. Senior Staff candidates typically bring 2+ years.
- Core AI Depth: Real hands-on depth in at least one core area: agent runtime, evaluation, retrieval, or observability and cost. At Staff and Senior Staff we look for depth in agent runtime or evaluation, and at Senior Staff a second deep area plus working knowledge across the rest.
- Evaluation Rigor: Experience measuring whether an AI system works with evaluation data, rather than "it seemed to work."
- Engineering Fundamentals: Strong production engineering across testing, debugging, services, APIs, deployment and on-call.
- Data & Security Fluency: Experience handling sensitive data with a security-first mindset.
- Comfort working in a greenfield space, and clear communication with technical and non-technical partners
Preferred Qualifications:- Regulated-Industry Experience: Healthcare (PHI, HIPAA), finance or insurance.
- GCP Experience: Running production services on Google Cloud.
- Model Operations: Experience migrating a system between model versions or providers.
- Classic ML Background: Machine learning experience beyond LLMs.
- Internal Platforms: Built a platform used by other engineering teams.
- Team Leadership: For Senior Staff, experience leading a small team's technical direction from zero and growing a single pod into multiple teams.
Our BenefitsIn addition, for salaried positions you would also be eligible for:
- Medical, Dental, and Vision plans
- Flexible Spending/Health Savings Accounts
- Flexible PTO
- 401(k) + Company Match
- Life Insurance, Pet insurance, and more
