Letta
Research Engineer / Scientist, Memory
San Francisco Office · Full-time · Posted Sep 10, 2025
About the job
Design and research long-term memory architectures for LLM agents, including memory systems, multi-agent sharing, context management, and evaluation.
What you'll do
- Define abstractions for the LLM memory layer and build architectures for temporal, episodic, semantic, and procedural memory.
- Research memory sharing for multi-agent collaboration and improve context management.
- Run evaluations to measure and improve agent memory; publish research and open-source work.
What they ask for
- Deep expertise in LLMs and retrieval.
- Track record of impactful research through breakthrough publications and/or open-source contributions.
- Ability to balance execution speed with empirical rigor.
- Real-world impact beyond pure academic work.
Tools
LLMs
AI focus
Research and develop self-improving AI agents with long-term memory, learning, and adaptation.
Model-written summary · the original posting is authoritative