Research Engineer / Scientist, Memory

Letta • San Francisco, CA

107d

About The Position

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, we are backed by notable figures in 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. This role is in-person (no hybrid), 5 days a week in downtown San Francisco.

Requirements

• Deep expertise in LLMs and retrieval.
• Track record of impactful research (breakthrough publications and/or open source contributions).
• Ability to balance execution speed with empirical rigor.
• Real-world impact beyond pure academic work.

Responsibilities

• Design the long-term memory architecture for LLMs.
• Define the key abstractions of the LLM memory layer.
• Build memory architectures that support multiple memory types including temporal sequences, episodic experiences, semantic knowledge, and procedural skills.
• Research memory sharing between multiple agents that enable effective multi-agent collaboration.
• Improve context management techniques that solve the long-context / context derailment problem.
• Run evaluations for measuring and improving memory for agents.

What This Job Offers

• Job Type: Full-time
• Career Level: Entry Level
• Number of Employees: 1-10 employees