The company's AI team is creating the infrastructure that lets agents be evaluated and improved over time.
This full-stack role leans toward the backend. You will own core systems and also ship product features and collaborate directly with enterprise customers.
Responsibilities
Design the backend services and data models for evaluation datasets, experiment runs, agent traces, knowledge versions, findings, and quality criteria that customers define.
Build and maintain enterprise integrations covering authentication, OAuth, webhooks, incremental syncs, backfills, rate limits, retries, and monitoring.
Take features from technical design and implementation through deployment, monitoring, customer feedback, and later iterations.
Talk with customers about how their systems work, troubleshoot their problems, and convert their particular needs into capabilities other customers can use.
Work across the stack to build product interfaces that make the underlying systems practical to use.
Requirements
You have at least 2 years of experience building and shipping production systems as a backend or full-stack engineer.
You have worked in production with TypeScript, Node.js or Bun, PostgreSQL, and job queues or worker systems.
You have worked at a startup that moves quickly and have a record of owning projects from design through deployment and iteration.
You have hands-on machine learning engineering experience, including building models.
You have built enterprise integrations involving OAuth flows, webhooks, incremental syncs, backfills, and rate-limit handling.
Production experience with agent infrastructure, LLM evaluation, tracing, or agent memory systems is valuable.
Conditions
Base salary ranges from $120,000 to $180,000 per year.
Visa sponsorship is available.
The role is on-site in San Francisco, California, United States.