Senior AI Engineer

Zep is the context engineering platform for AI agents (YC W24). We've achieved 50% month-over-month ARR growth with 240+ customers including Fortune 500s. Our open-source project Graphiti has over 24,000 GitHub stars and is foundational infrastructure for agent memory systems.

The Role:

This is a senior backend role centered on building low-latency systems and operating them at scale on AWS. You'll develop LLM-powered capabilities while contributing to Graphiti, our context graph framework. This role is for engineers with proven production experience taking LLM applications from prototype to deployed systems. It is not a role for ML researchers or data scientists.

What you'll do:

• Ship end-to-end product features across backend services, APIs, and data flows.
• Build and operate LLM systems including extraction pipelines and evaluation harnesses.
• Contribute to system design documentation and iteration cycles.
• Improve production quality across performance, observability, and operational procedures on AWS.

Requirements:

• 6+ years of production engineering with a strong backend systems background.
• Master's in Computer Science or equivalent.
• Go and Python proficiency in critical-path code.
• Hands-on AI agent and LLM application experience with non-trivial production deployments.
• Spec-driven agent coding and harness development.
• Hands-on AWS production operations.
• Familiarity with at least one agent SDK (LangGraph, Google ADK, Mastra), vector stores, and evaluation tooling.

Tech stack: Go, Python, TypeScript, AWS.

Not a fit if:

• Your LLM experience involves only single-turn chat or RAG features.
• Your background emphasizes ML research over production agent systems.
• You have limited experience operating backend systems with real throughput/latency demands.

Compensation: $180K - $250K + 1.00% - 1.50% equity. Location: San Francisco / Remote (US).