Clera
Agent Engineer
About this role
Build and own core agent infrastructure for a medical tourism startup, designing orchestration layers, tool integrations, and evaluation systems that power patient-facing and internal AI agents. This systems-focused role emphasizes automating clinic and operational workflows end-to-end.
What you'll do
- Design and implement orchestration layers for multi-step agentic workflows across clinic and internal operations
- Integrate external tools and APIs into agent systems with robust error handling
- Build retrieval and evaluation infrastructure to measure and improve agent reliability
- Identify opportunities to automate manual work and ship systems to eliminate them
- Monitor agent performance in production and iterate on system design based on real-world behavior
What they're looking for
- Agent and LLM systems development
- Orchestration and workflow design
- Tool and API integration
- Retrieval-augmented generation (RAG)
- Evaluation frameworks and monitoring systems
- Python or similar backend language
- Systems thinking and automation mindset
- Computer science fundamentals
Benefits
- Meaningful equity compensation
- Full-time position with on-site work in San Francisco
- Infrastructure-focused role with clear ownership
- Opportunity to build foundational systems at early-stage startup
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Clera
Clera builds an agentic operating system that automates complex workflows and processes through AI agents, with a platform designed to simplify distributed infrastructure management for developers. The company is hiring Founding Engineers, Customer Engineers, and Product Engineers to develop both backend systems and user-facing interfaces across their AI automation products.
View all jobs at CleraLikely interview questions
- Walk us through a project where you built or significantly contributed to an agent or LLM system—what was the orchestration approach and how did you handle tool integrations?
- Describe your experience designing evaluation frameworks or monitoring systems for agent reliability. What metrics did you track and how did you iterate based on them?