Job Description

About the Role

Build and own agent infrastructure for an AI-driven services company. You will help make agents reliable in production, with durable context, trustworthy evaluations, and clear paths for human intervention.

What You'll Do

• Build and maintain infrastructure that helps agents execute tasks reliably across many iterations.
• Design memory and retrieval systems that preserve useful context from messy operational data over time.
• Develop evaluation harnesses that teams can use to make production deployment decisions.
• Measure, test, troubleshoot, and improve agent systems, including failure recovery and retries.
• Ship agent systems to customers and iterate based on production feedback.
• Contribute across infrastructure, orchestration, customer collaboration, and 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 hands-on experience building production systems.
• Experience implementing agent memory and context retrieval for real operational data, not only demo datasets.
• Experience building evaluation harnesses used to guide production deployment decisions.
• Experience with agent orchestration, infrastructure, workflow management, or agent tooling.
• Experience implementing production reliability patterns, including failure recovery and retry logic.
• Evidence of technical ownership, such as taking a project from conception to production, founding or leading a technical project, or contributing to open-source agent tooling or LLM infrastructure.
• Early engineering experience at a high-growth or AI-focused startup, experience building complex production systems, or a strong technical education background.

Compensation & Benefits

$150,000 to $250,000 USD base salary, plus meaningful early equity. Visa sponsorship and relocation support are available.

Location

On-site in San Francisco, United States.