Quick Overview
Job Description
About the Role
Own the agent infrastructure that helps AI systems execute tasks reliably, retain context, and involve people when needed. You will build and ship production systems, using real-world feedback to improve how agents plan, recover, and perform.
What You'll Do
Build and maintain infrastructure for reliable agent execution across long-running, multi-step tasks.
Design memory and retrieval systems that work with messy operational data and preserve useful context over time.
Develop evaluation harnesses that teams can trust when deciding whether to deploy LLM systems.
Measure, test, debug, and improve agent systems throughout the development and production lifecycle.
Collaborate with customers and teammates to iterate on production agents, orchestration, and reliability.
What We're Looking For
At least 3 years of experience building and shipping LLM agents that run unattended in production for real users.
Strong Python skills and experience building production systems and agent infrastructure.
Experience developing evaluation harnesses used to inform production deployment decisions.
Hands-on background with agent memory, context retrieval for operational data, and orchestration or workflow systems.
Experience implementing failure recovery, retries, or other production reliability patterns for agents.
Experience building agent tools, frameworks, or libraries; a technical project taken from idea to production is also relevant.
Compensation & Benefits
Base salary of $150,000 to $250,000 USD annually, plus meaningful early equity. Visa sponsorship is available.
Location
On-site in San Francisco, United States.