Solving Self-Improving Superintelligence

The human brain is a sponge. Today’s AI brains are brittle and rigid. At Letta, we’re building self-improving artificial intelligence: creating agents that continually learn from experience and adapt over time.

Founded by the creators of MemGPT from UC Berkeley’s Sky Computing Lab (the birthplace of Spark and Ray). Backed by Jeff Dean, Clem Delangue, and pioneers across AI infrastructure. Our agents already power production systems at companies like 11x and Bilt Rewards, learning and improving every day.

We’re assembling a world-class team of researchers and engineers to solve AI’s hardest problem: making machines that can reason, remember, and learn the way humans do.

Note that this role is in-person (no hybrid), 5 days a week in downtown San Francisco.

We are building the developer stack for agents that can run in production applications, not just demo notebooks. As a Software Engineer, you will bridge the gap bleeding-edge agent systems and production-grade software for running agents in real applications. You will help define developer APIs for agents, and lead development of our company’s OSS stack as well as the hosted service.

Responsibilities:

• Develop Letta's OSS agents framework and cloud service

• Design scaleable & resilient backend services and APIs to support Letta Cloud

• Work with researchers and support bleeding-edge agent architectures in Letta

Required skills:

• Strong proficiency with Python

• Strong understanding of how to architect services for security, reliability, and performance

• Ability to build scaleable backend services

• Strong understanding of SQL databases (Postgres)

• Familiarity with tooling across the AI stack, such as inference engines (e.g. vLLM, Ollama), and LLM provider APIs (OpenAI, Anthropic)

• Bonus: proficient with TypeScript, React, Tailwind, etc. (the modern stack for web applications)