← All roles

Research Engineer / Scientist, Self-Improvement

Letta· Technical Staff - Research
Apply on company site
San Francisco, CAFull timePosted 11mo ago

About the role

Role focused on developing methods for self-improving agents and advancing self-improving superintelligence through research, implementation, and open dissemination of findings.

Responsibilities

  • Develop prompt optimization and system prompt learning methods that allow agents to continuously learn from long-horizon tasks
  • Develop methods that allow agents automatically generate and test out hypotheses in an environment, or seek out and improve their own weaknesses
  • Improve the efficiency of learning from long-running agentic tasks
  • Design and run experiments to measure self-improvement at scale

Qualifications

  • Expertise in machine learning, in particular LLMs and continual learning
  • Familiarity with agent frameworks and prompt optimization
  • 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

Skills

Required:Machine learning (LLMs and continual learning)Agent frameworks and prompt optimization
Last updated Jun 15, 2026. Interested? Apply on the company site.

About Letta

The platform for stateful agents. Build AI agents with long-term memory, advanced reasoning, and custom tools using the Letta API and Agent Development Environment (ADE).

Letta is the platform for building stateful AI agents that can continually learn from experience and evolve over time.

AIAgentsMemoryDevelopment EnvironmentAPISDKs
Company profileWebsite

More open roles at Letta