Research Engineer/Scientist, Self-Improvement

Responsibilities

• Developing prompt optimization and system prompt learning methods for long-horizon tasks
• Developing methods for agents to automatically generate and test hypotheses or improve weaknesses
• Improving the efficiency of learning from long-running agentic tasks
• Designing and running experiments to measure self-improvement scalably
• Advancing the field through open publishing of research, papers, and open-source code

Requirements

• Expertise in machine learning, specifically LLMs and continual learning
• Familiarity with agent frameworks and prompt optimization
• Track record of impactful research or open-source contributions
• Ability to balance execution speed with empirical rigor
• Focus on real-world impact beyond pure academic work

About the Company

Founded by the creators of MemGPT from UC Berkeley’s Sky Computing Lab, Letta is building self-improving artificial intelligence. We create agents that continually learn from experience and adapt over time to solve the hardest problems in AI.