3 hours ago
Base Salary
$150k - $250k/yr
Responsibilities
- Build and maintain infrastructure that enables agents to complete multi-step tasks reliably.
- Design memory and retrieval systems that preserve relevant context from complex operational data.
- Develop evaluation harnesses to support 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 to orchestration, infrastructure, customer collaboration, and technical team growth.
Requirements
- 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 informed production deployment decisions.
- Hands-on experience with 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.
Benefits
- Base salary of $150,000 to $250,000 USD annually, with meaningful early equity.
- Relocation assistance and visa sponsorship are available.
- On-site position in San Francisco, United States.