You would join an AI team that builds the server-side systems and product interfaces for tools that test and improve AI agents.
This role leans toward backend work but spans full-stack. You would help shape architecture and product direction while turning complicated systems into features enterprise customers can use.
Responsibilities
Create and run server-side systems that evaluate agents and help them get better over time.
Model the data behind evaluation sets, experiment runs, agent traces, knowledge versions, findings, and quality criteria that customers define.
Build and operate integrations with enterprise platforms, covering login and OAuth, webhooks, incremental and historical syncs, rate limits, retries, and monitoring.
Carry features from design and coding through release, monitoring, customer feedback, and later revisions.
Talk with customers about their systems, track down problems, and convert their particular needs into capabilities other customers can reuse.
Build full-stack features that make the underlying systems easy to reach and put to use.
Requirements
At least 2 years of experience building and shipping production software as a full-stack or backend engineer.
Production work with TypeScript, Node.js or Bun, PostgreSQL, and job queues or worker systems.
Experience at a fast-moving startup, owning projects from design through release and iteration.
Experience building enterprise integrations that involve OAuth, webhooks, incremental syncs, backfills, and rate-limit handling.
Hands-on work with agent infrastructure, LLM evaluation, tracing, or agent memory systems is valuable.
Engineering experience at an early-stage company, including owning backend systems end to end, is relevant. AI side projects, open-source contributions, and hackathon participation are also relevant.
Conditions
Base salary ranges from $120,000 to $180,000 per year.