SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
OpenLoop is building telehealth infrastructure to deliver virtual care across all 50 US states. The company is hiring Applied AI Engineers to build production LLM-based agents and systems that real patients and healthcare providers depend on.
In this role, you will:
- Build and deploy production LLM agents and assistants (not prototypes) that handle real healthcare workflows
- Design and implement agent runtime and orchestration systems, including tool calling, context management, failure handling, retries, timeouts, and sandboxing
- Create evaluation frameworks, test harnesses, regression tests, and AI-graded evaluations to measure improvements and catch regressions before users encounter them
- Manage access to multiple LLM providers, handle version upgrades, and plan fallback strategies when providers fail
- Build observability and cost-tracking systems to trace agent behavior in production and attribute AI spend to specific use cases
- Implement grounding and retrieval (RAG) systems to connect agents to real company data, ensuring answers are fact-based
- Partner with operations teams to identify which workflow steps agents can reliably handle and when to escalate to humans
- Ensure security, privacy, and safety of patient data (PHI) in all AI systems, control agent access, and defend against prompt injection and misuse
- Build on Google Cloud Platform and work with data platform teams to access governed data
- Contribute to code and design reviews, mentor engineers newer to AI
- Communicate AI trade-offs clearly to product, operations, and clinical stakeholders
OpenLoop operates with a flat organizational structure and core values of Autonomy, Competence, and Belonging.
REQUIREMENTS:
Required:
- Bachelor's degree in Computer Science, Engineering, or related technical field
- 5 to 15+ years of software engineering experience
- Hands-on experience building and running LLM-based systems in production (not demos, prototypes, or personal projects); Senior Staff candidates typically bring 2+ years of production LLM experience
- Real hands-on depth in at least one core area: agent runtime, evaluation, retrieval, or observability and cost
- Experience measuring AI system effectiveness with evaluation data (not subjective assessment)
- Strong production engineering fundamentals: testing, debugging, services, APIs, deployment, on-call
- Experience handling sensitive data with a security-first mindset
- Comfort working in greenfield environments and clear communication with technical and non-technical partners
Preferred:
- Experience in regulated industries (healthcare/PHI/HIPAA, finance, insurance)
- Production experience on Google Cloud Platform
- Experience migrating systems between model versions or providers
- Machine learning background beyond LLMs
- Experience building internal platforms used by other engineering teams
- For Senior Staff: experience leading a small team's technical direction and growing a single pod into multiple teams
