About the Role
Own the agent infrastructure that helps AI systems execute tasks reliably, retain useful context over time, and involve people when needed. You will work across agent orchestration, memory, evaluation, and production reliability, shipping systems for real users and improving them through production feedback.
What You'll Do
Build and maintain infrastructure that lets agents execute tasks reliably across many iterations.
Design memory and retrieval systems that preserve client context from messy operational data.
Develop evaluation harnesses that teams can use to make production deployment decisions.
Measure, test, troubleshoot, and improve agent systems, including failure recovery and reliability.
Collaborate with customers and contribute to infrastructure, orchestration, and team growth as needed.
What We're Looking For
At least 3 years building and shipping LLM agents that ran unattended in production for real users.
Experience building evaluation harnesses used to guide production releases.
Strong Python skills for production systems, plus hands-on experience with agent orchestration, infrastructure, or workflow management.
Experience implementing memory and context retrieval for operational data, beyond demo datasets.
Experience with agent tooling, frameworks, or libraries, and production patterns for retries, failure recovery, and reliability.
A track record of taking a technical project from conception to production; open-source agent tooling or LLM infrastructure experience is a plus.
Compensation & Benefits
Base salary is $150,000 to $250,000 USD annually, plus meaningful early equity. Visa sponsorship is available.
Location
On-site in San Francisco, United States.