AI Engineer

About the role

Join a fast-growing technology company building production AI agents that actually run at scale.

Tasks

• Build and maintain the core infrastructure that enables agents to execute tasks reliably, even after dozens of iterations.
• Design and implement memory systems that retain months of client context from real operational data.
• Develop evaluation harnesses that teams can trust to make production decisions.
• Own the full development loop: build, measure, test, improve and make it learn.
• Ship agent systems for real customers and iterate based on production feedback.
• Work across infrastructure, orchestration, customer collaboration and hiring as the team grows.

Requirements

• Strong Python development skills
• Hands-on experience with LLM agents deployed in production
• Agent orchestration, retrieval & long-term memory systems
• AI evaluation frameworks and production reliability
• A proven ability to build, deploy and scale AI solutions
• Proven experience shipping LLM agents that ran unattended in production for real users.
• Experience building evaluation harnesses used to make shipping decisions.
• Hands-on experience with retrieval and memory systems for real, complex operational data.
• Strong Python proficiency and experience with agent orchestration and infrastructure.
• Execution-oriented mindset with a track record of delivering results. Bonus if you have open-source contributions or have founded a project.

Schedule

• On-site
• Full-time

Pay

• $150,000–$250,000 USD/year

Benefits

• Equity
• Relocation assistance provided
• Visa sponsorship available

How to apply

• Send your resume by email.

Location

• San Francisco, CA