About the Role
Join an early-stage team building AI infrastructure for service businesses. As an Applied AI Engineer, you will own the systems that help agents execute tasks reliably, retain useful context, and involve people when needed. Your work will shape how agent systems plan, recover from failures, and improve in production.
What You'll Do
Build and maintain infrastructure that enables agents to complete tasks reliably across many steps.
Design memory and retrieval systems that preserve relevant context from complex operational data.
Develop evaluation harnesses that teams can use to make informed production release decisions.
Measure agent performance, investigate failures, and improve reliability and recovery patterns.
Ship agent systems to customers and iterate based on production feedback.
Contribute across orchestration, infrastructure, customer collaboration, and technical team growth.
What We're Looking For
At least 3 years of experience building and shipping LLM agents that ran unattended in production for real users.
Strong Python skills and experience building production systems.
Experience creating evaluation harnesses that have informed production deployment decisions.
Hands-on background in agent orchestration, infrastructure, workflow management, or reliability engineering.
Experience with retry logic, failure recovery, and other production reliability patterns for agents.
Experience building memory and context retrieval systems for messy operational data, beyond demo datasets.
Experience developing agent tools, frameworks, or libraries; open-source contributions or leading a technical project from idea to production are also relevant.
Compensation & Benefits
Base salary is $150,000 to $250,000 USD annually, with meaningful early equity. Relocation assistance and visa sponsorship are available.
Location
This is an on-site position in San Francisco, United States.