SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
OpenLoop is a telehealth platform that delivers virtual care solutions across all 50 US states. You'll be the first technical leader for AI at the company, joining the AI Platform pod as one of the earliest hires.
In this hands-on role, you'll set the technical foundation for how AI agents operate across the organization. You'll own multiple core AI engineering disciplines: agent runtime and orchestration, evaluation systems, model operations, observability, and data grounding. Your decisions now will shape how other teams build on top of your work.
Key responsibilities include:
- Setting technical direction for agent runtime, orchestration, and framework decisions (build vs. adopt)
- Building evaluation systems with regression tests and AI-graded evals to measure actual performance
- Managing model access, routing across providers, version upgrades, and provider failover planning
- Owning observability and cost attribution for AI systems
- Building retrieval and grounding systems over company data to ensure factual agent responses
- Partnering with business and ops teams to convert human workflows into agent workflows
- Ensuring patient data protection and HIPAA compliance across all AI systems
- Making infrastructure decisions on GCP and coordinating with the Data Platform team
- Mentoring new AI engineers and raising technical standards through code and design review
- Communicating AI trade-offs and limitations clearly to product, operations, and clinical stakeholders
You'll partner closely with an AI Engineering Manager who handles people and delivery while you own architecture and technical quality. The AI Platform pod will eventually split into AI Infrastructure and AI Tools teams, and you'll carry long-range technical direction until an AI Principal Engineer is hired.
Requirements:
- 12+ years of software engineering experience with real technical leadership experience (tech lead, staff, or principal-level scope)
- 2+ years building and running LLM-based systems in production (not demos or personal projects)
- Deep, hands-on expertise in agent runtime or evaluation, plus working knowledge across the AI engineering stack
- Track record of measuring AI quality with real evaluation methods and data
- Experience leading a small team's technical direction from zero or near-zero
Preferred qualifications:
- Healthcare or regulated-industry experience (PHI, HIPAA)
- GCP experience
- Experience building internal platforms used by other engineering teams
- Background in classic machine learning in addition to LLMs
- Experience scaling a team from a single pod into multiple teams
