Research Engineer / Scientist, Post-Training
San Francisco Office • FullTime
Posted 1y ago
Job Location
San Francisco Office
Tech Stack
Remote Work Policy
On-site
Employment Type
FullTime
Categories
AI Research Engineer
About the job
Letta is building self-improving artificial intelligence, creating agents that continually learn from experience and adapt over time. Founded by the creators of MemGPT, our agents already power production systems and learn daily. We are assembling a world-class team of researchers and engineers to solve AI's hardest problem: making machines that can reason, remember, and learn like humans. This role will pioneer post-training techniques to improve LLM integration into agentic systems, advancing the field through open publishing and code.
Responsibilities
- Train models for better agentic tool-use, particularly for context management.
- Design mechanisms for continuous model weight updates post-deployment without catastrophic forgetting.
- Design and run experiments to improve understanding of the interplay between data mixtures, training algorithms, and models.
- Build infrastructure for generating and collecting synthetic data at scale.
- Build challenging evals for measuring agentic capabilities.
Requirements
- Proficiency in Python and deep learning frameworks like PyTorch.
- Expertise in post-training techniques such as SFT fine-tuning, reinforcement learning, reward models, and preference learning.
- Ability to balance execution speed with empirical rigor.
- Proven track record of impactful research, including breakthrough publications and/or open-source contributions.
- Demonstrated real-world impact beyond pure academic work.