Research Engineer Scientist Memory
Letta is a San Francisco AI company building persistent, stateful agents that learn from experience through memory, identity, and evolving capabilities.
Funding history
About Letta
Letta develops and operates an AI agent platform, including Letta Agent and open-source Letta Code, for building, deploying, and using stateful agents across local and cloud environments.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will define LLM memory-layer abstractions and build architectures for temporal, episodic, semantic, and procedural memory. You will research memory sharing for multi-agent collaboration, improve context management, run evaluations, and publish research through papers, reports, blog posts, and open-source code.
Requirements
- LLM
- Retrieval
- Impactful research
- Publications
- Open-source contributions
- Empirical rigor
- Real-world impact
Responsibilities
- Define key abstractions for the LLM memory layer
- Build memory architectures for temporal, episodic, semantic, and procedural memory
- Research memory sharing for multi-agent collaboration
- Improve context-management techniques for long-context challenges
- Run evaluations to measure and improve agent memory
- Publish research through papers, technical reports, blog posts, and open-source code
Hiring Process
Initial screen (30 min) → technical screen (1–1.5 hours) → paid in-person work trial (2 days onsite in San Francisco).