Staff Engineer at Zep – San Francisco, California

Zep is a context engineering platform for AI agents. We help developers build personalized, reliable AI applications by assembling the right context from chat history, business data, and user behavior.
We’re hiring a Staff Engineer to own core backend architecture and execution. This role is for someone who can design and ship low-latency systems at scale, operate them in production on AWS, and build agent-facing capabilities that hold up in high-throughput environments.
Responsibilities
- Ship end-to-end product features: backend services, APIs, data flows, and the supporting UI where needed.- Build and operate agent-facing capabilities: workflows, tooling, evaluation harnesses, and reliability improvements for real agent systems.- Own and collaborate on system design and implementation for new components: make pragmatic architecture decisions, document them, and iterate.- Improve production quality: performance, observability, and operational runbooks on AWS.
Requirements
- Strong backend systems background. You’ve designed and shipped production services with high throughput and strict latency targets.- Go and Python experience in real systems. You can own critical-path code and performance work.- Agent building experience: you’ve built agentic applications end-to-end and understand reliability, evaluation, and failure modes in production.- Hands-on AWS experience operating production systems (deployments, monitoring, scaling, cost and reliability tradeoffs).
Nice to have
- TypeScript experience (frontend or SDK work).
Salary: $175,000 - $250,000 per year + Stock OptionsBenefits: Health, Dental, Vision Insurance; 401K match; Phone Benefits