About the roleYou'll be the first technical leader for AI at OpenLoop. You're joining the AI Platform pod as one of the earliest hires, which means the decisions you make now become the foundation everyone else builds on: how our AI agents run, how we know if they're actually good, how we keep them safe and affordable, and how other teams build on top of what you create.
This pod will eventually split into two teams, AI Infrastructure and AI Tools, so we need someone who can go deep in at least two of the core AI engineering disciplines while staying credible across all of them. Until we hire an AI Principal Engineer, you'll also carry the long-range technical direction for AI across the whole company. This is a hands-on role. You'll write code and review designs, not just draw boxes on a whiteboard.
You'll partner closely with the AI Engineering Manager, who owns people and delivery while you own architecture and technical quality.
What you'll do- Set the technical direction for agent runtime and orchestration: how agents call tools, hold context, and hand off work, and whether we build or adopt frameworks to do it
- Build the evaluation systems that prove our AI is actually good, not just "seems to work," including regression tests and AI-graded evals
- Make the call on model access and operations: routing across providers, managing version upgrades, and planning for what happens when a provider goes down
- Own observability and cost: tracing what agents did and why, and attributing AI spend so nobody gets a surprise bill
- Build retrieval and grounding over real, messy company data so agents answer with facts, not guesses
- Work with business and ops teams to turn human workflows into agent workflows, and decide what should always stay with a person
- Keep patient data protected in every AI system you touch. This is healthcare, so security and privacy aren't optional
- Make sound calls on cloud and data infrastructure (we run on GCP) and partner well with the Data Platform team
- Raise the bar through code and design review, and mentor engineers who are new to AI
- 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"
Who you are- 12 or more years of software engineering experience, with real technical leadership experience (tech lead, staff, or principal-level scope)
- Two or more years building and running LLM-based systems in production, not just demos or personal projects
- Deep, hands-on expertise in agent runtime or evaluation, plus working knowledge across the rest of the AI engineering stack
- A track record of measuring AI quality with real evaluation methods and data, not vibes
- Experience leading a small team's technical direction from zero, or close to it
Preferred- Healthcare or other regulated-industry experience (PHI, HIPAA)
- GCP experience
- Experience building an internal platform used by other engineering teams
- Background in classic machine learning as well as LLMs
- Experience scaling a team from a single pod into multiple teams
What We Offer- Competitive compensation
- Medical, Dental & Vision
- Flexible Spending / Health Savings Accounts
- Generous PTO and hybrid-work flexibility
- 401(k) with Company Match
- Life Insurance, Pet Insurance, and more
