Skip to main content

Clera

Applied AI Engineer

San Francisco$150k–$250kfulltimemidAdded today

About this role

Lead engineer at a seed-stage AI startup responsible for building the core infrastructure that powers reliable agent execution in production. You'll design memory systems, evaluation frameworks, and orchestration layers while shipping real systems for customers and helping scale the early team.

What you'll do

  • Build and maintain core infrastructure enabling agents to execute tasks reliably across many iterations
  • Design memory systems that retain months of client context from real-world operational data
  • Develop evaluation harnesses trusted for production deployment decisions
  • Own the full development cycle: build, measure, break, fix, and iterate based on production feedback
  • Ship agent systems for real customers and drive continuous improvement
  • Contribute to infrastructure decisions, hiring, and team scaling

What they're looking for

  • LLM agents and production deployment
  • Python for production systems
  • Evaluation harness design and implementation
  • Retrieval and memory systems
  • Agent orchestration and workflow management
  • Failure recovery and retry logic patterns
  • Human-in-the-loop systems
  • System reliability and observability

Benefits

  • Base salary $150,000–$250,000 annually
  • Meaningful early-stage equity
  • Relocation assistance
  • Visa sponsorship available
Apply with Autofill

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 Clera

Likely interview questions

  • Walk us through a production LLM agent system you shipped—what broke first and how did you fix it?
  • How have you built evaluation harnesses that teams actually used to gate production deployments?