Letta
Research Engineer / Scientist, Memory
San Francisco Office. Posted 14 months ago
The role
You will design the long-term memory architecture for LLMs. You will work with a team of AI researchers and engineers to advance the field through open publishing of research.
What you will do
- Defining the key abstractions of the LLM memory layer
- Building memory architectures that support multiple memory types including temporal sequences, episodic experiences, semantic knowledge, and procedural skills
- Researching memory sharing between multiple agents that enable effective multi-agent collaboration
- Improving context management techniques that solve the long-context / context derailment problem
- Running evaluations for measuring and improving memory for agents
Required qualifications
- 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
Before you apply
- Initial screen (30 min)
- Technical screen (1-1.5 hours)
- Paid in-person work trial (2 days onsite in SF)
About the company
Letta was founded by the creators of MemGPT from UC Berkeley’s Sky Computing Lab. The company is building self-improving artificial intelligence agents.