Join a small, highly technical team building AI agent evaluation and continuous-improvement infrastructure for enterprise customers. This backend-leaning full-stack role focuses on making agent systems more reliable by connecting production performance with the knowledge and workflows that can improve it.
Build and improve backend systems for agent evaluation and continuous improvement.
Design data models for evaluation datasets, experiment runs, agent traces, knowledge versions, findings, and customer-defined quality criteria.
Own enterprise integrations from authentication and synchronization through 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 specific needs into reusable product capabilities.
Deliver full-stack features, including the product interfaces that make backend systems useful.
Three to six years of experience as a backend-leaning full-stack software engineer, including production systems built for enterprise customers.
Professional TypeScript experience and comfort across frontend and backend development; Python experience is preferred.
Experience with React, relational and vector databases, and cloud environments.
A bachelor's degree in computer science or a related field.
Experience at both a large company and an early-stage startup with fewer than 50 employees, including meaningful ownership.
Background in AI agents, LLMs, evaluation, or quality assurance is helpful; founder experience or hackathon participation is also valued.
Existing US work authorization is required. Immediate visa transfer or sponsorship is not available.
Salary range: $180,000 to $200,000 USD annually.
On-site in San Francisco, California.
Job details are sourced from the employer's original posting.
Open job postingAbout the company
A talent solutions partner that helps companies build and scale their teams.