Senior Staff Applied AI Engineer

• Agent Runtime & Orchestration: Set the technical direction for how agents run, call tools, hold context and hand off work, including failure handling, retries, timeouts and sandboxing. Decide when to build and when to adopt frameworks.
• Evaluation: Build the systems that prove our AI is actually good, including regression tests and AI-graded evals, and help each team define what "good" means for their agents.
• Model Access & Operations: Set up access to models from multiple providers, route between them, 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 with budgets and guardrails.
• Grounding & Retrieval: Connect agents to real, messy company data and documents through retrieval (RAG), context design and prompt engineering, so answers are based on facts.
• Workflow Design: Partner with operations teams to turn human workflows, such as patient support, into agent workflows, and decide which steps should stay with 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: Make sound infrastructure decisions on GCP and partner with the Data Platform teams who provide the governed data agents use.
• Technical Leadership: Set and document direction when the right answer is unclear, make build-versus-buy calls and revisit them as tools change, keep the platform general enough for many teams, and mentor engineers who are new to AI through code and design review.
• 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.

• Bachelor's degree in Computer Science, Engineering, or a related technical field
• Proven Technical Leadership: 12+ years of software engineering experience, with a track record at tech lead, staff or principal-level scope.
• Production LLM Experience: 2+ years building and running LLM-based systems in production that real users relied on, not only demos, prototypes or personal projects.
• Core AI Depth: Deep, hands-on expertise in agent runtime or evaluation, a second area of real depth, and working knowledge across the rest of the AI engineering stack.
• Evaluation Rigor: A track record of measuring AI quality with real evaluation sets and test harnesses, and reporting results with numbers.
• Zero-to-One Leadership: Experience leading a small team's technical direction from zero, or close to it, in a greenfield setting.
• Excellent communication skills with the ability to explain complex technical concepts and trade-offs to non-technical stakeholders

• Regulated-Industry Experience: Healthcare (PHI, HIPAA), finance or insurance.
• GCP Experience: Running production services on Google Cloud.
• Internal Platforms: Built a platform used by other engineering teams.
• Team Scaling: Helped grow a single pod into multiple teams.

• Medical, Dental, and Vision plans
• Flexible Spending/Health Savings Accounts
• Flexible PTO
• 401(k) + Company Match
• Life Insurance, Pet insurance, and more

About OpenLoop

OpenLoop was co-founded by CEO, Dr. Jon Lensing, and COO, Christian Williams, with the vision to bring care anywhere. Our telehealth support solutions are thoughtfully designed to streamline and simplify go-to-market care delivery for companies offering meaningful virtual support to patients across an expansive array of specialties, in all 50 states.

Our company

We have a relatively flat organizational structure here at OpenLoop. Everyone is encouraged to bring ideas to the table and make things happen. This fits in well with our core values of Autonomy, Competence and Belonging, as we want everyone to feel empowered and supported to do their best work.

Sound like a good fit? We’d love to meet you.