About the Role
Join an AI infrastructure team building production monitoring for AI agents. You will shape how teams identify, prioritize, and resolve agent failures, helping make AI systems more reliable and easier to operate.
What You'll Do
Turn high volumes of signals into a focused set of issues teams should address.
Own the workflow from detecting and prioritizing failures through alerting, triage, and resolution.
Connect the product with tools such as team messaging, issue tracking, code hosting, and coding agents.
Design workflows for people and agents to collaborate on resolving issues.
Build across the TypeScript stack, from core services to user-facing product experiences.
Work directly with customers and help establish engineering standards.
What We're Looking For
At least one year of experience shipping production software, with a track record of delivering useful products and working beyond a narrow specialty.
Strong full-stack TypeScript skills, including frontend and backend development.
Experience building and operating AI agents in production, with an understanding of agent behavior and failure modes.
Experience with high-volume event data, data pipelines, production observability, monitoring, and debugging, with attention to system costs.
Ability to take customer problems from discovery to shipped solutions, including making architectural decisions in ambiguous settings.
Relevant engineering work demonstrated through a portfolio or résumé; experience with code quality tooling, early-stage teams, or direct customer delivery is useful.
Compensation & Benefits
Base salary: $120,000 to $200,000 annually. Visa sponsorship is not available.
Location
On-site in San Francisco, California. The role requires working from the office six days per week.