← All roles

Research Engineer / Scientist, Post-Training

Letta· Technical Staff - Research
Apply on company site
San FranciscoFull timePosted 11mo ago

About the role

Pioneer post-training techniques to improve integration of LLMs into agentic systems. Collaborate with AI researchers and engineers to advance self-improving superintelligence, publish research, and contribute open-source code. In-person role in downtown San Francisco, five days a week.

Responsibilities

  • Training models for better agentic tool-use, particularly for context management
  • Designing mechanisms for continuous model weight updates post-deployment without catastrophic forgetting
  • Designing and run experiments to improve understanding of the interplay between data mixtures, training algorithms, and models
  • Building infrastructure for generating and collecting synthetic data at scale
  • Building challenging evals for measuring agentic capabilities

Qualifications

  • Proficiency in python and deep learning frameworks eg. PyTorch
  • Expertise in post-training techniques e.g. SFT fine-tuning, reinforcement learning, reward models, preference learning
  • Ability to balance execution speed with empirical rigor
  • Proven track record of impactful research (breakthrough publications and/or open-source contributions)
  • Real-world impact beyond pure academic work

Skills

Required:PythonPyTorchPost-training techniques
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