Quick overview
Job description
About the Role
Join a small, technical team building infrastructure for evaluating and continually improving enterprise AI agents. This backend-leaning full-stack role combines ownership of core systems with shipping the product features that make them useful to customers.
What You'll Do
Build backend systems for agent evaluation and continuous improvement.
Improve data models for evaluation datasets, experiment runs, agent traces, knowledge versions, findings, and customer-defined quality criteria.
Own enterprise integrations across authentication, OAuth, webhooks, data synchronization, backfills, rate limits, schema changes, retries, monitoring, and production support.
Take features from design and implementation through 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 experience as a backend-leaning full-stack software engineer, with substantial software engineering experience.
Experience at both a large company and an early-stage startup, with meaningful individual-contributor ownership.
Experience building production systems for enterprise customers, including data models, pipelines or queues, or integrations.
Comfort shipping user-facing features with TypeScript and React; Python experience is preferred.
Familiarity with relational databases, vector databases, and cloud environments.
A bachelor's degree in computer science or a related field.
Background in AI agents, LLMs, or evaluation and quality systems 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.