About the Role
Join a small, technical AI team building infrastructure that helps enterprise agents improve through evaluation and production feedback. This backend-leaning full-stack role offers ownership of core systems and the product features that make them useful.
What You'll Do
Build backend systems for agent evaluation and continuous improvement.
Develop data models for evaluation datasets, experiments, agent traces, knowledge versions, findings, and customer-defined quality criteria.
Own enterprise integrations, including authentication, OAuth, webhooks, syncs, backfills, retries, monitoring, and production support.
Take features from technical design through implementation, deployment, monitoring, customer feedback, and iteration.
Work with customers to diagnose issues and turn their needs into reusable product capabilities.
What We're Looking For
Three to six years of substantial backend-leaning full-stack engineering experience, with a strong individual-contributor focus.
Experience working at both a large company and an early-stage startup, with meaningful ownership in a startup environment.
Production experience building enterprise systems, especially data models, pipelines or queues, and integrations.
Comfort shipping user-facing features with TypeScript and React; Python experience is preferred.
Familiarity with relational and vector databases and cloud environments.
A bachelor's degree in computer science or a related field, plus experience working in the United States.
Experience with agent evaluation, LLMs, or evaluation and quality assurance is helpful.
Compensation & Benefits
Base salary is $180,000 to $200,000 annually. Visa sponsorship is available.
Location
On-site in San Francisco, California, United States.