Research Engineer Scientist Self Improvement
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 develop prompt-optimization and system-prompt-learning methods for agents. You will create methods for hypothesis testing and self-improvement, improve learning efficiency for long-running agentic tasks, run scalable experiments, and publish research through papers, reports, blog posts, and open-source code.
Requirements
- Machine learning
- LLM
- Continual learning
- Agent framework
- Prompt optimization
- Impactful research
- Publications
- Open-source contributions
- Empirical rigor
- Real-world impact
Responsibilities
- Develop prompt-optimization and system-prompt-learning methods for continuous learning from long-horizon tasks
- Develop methods for agents to generate and test hypotheses and improve their weaknesses
- Improve learning efficiency for long-running agentic tasks
- Design and run scalable experiments to measure self-improvement
- 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).