Research Scientist
| Company | Letta |
|---|---|
| Location | San Francisco, CA, USA |
| Salary | $Not Provided – $Not Provided |
| Type | Full-Time |
| Degrees | |
| Experience Level | Senior, Expert or higher |
Requirements
- Strong understanding of LLMs (Large Language Models)
- Experience in R&D processes related to AI and machine learning
- Knowledge of context management techniques
- Familiarity with model evaluation and finetuning
- Experience in writing technical reports and blog posts
Responsibilities
- R&D of the core agent framework, including context management techniques used to prompt the LLMs within the agent framework
- Prototyping new context management and memory systems (e.g. better state→prompt compilers, more complex memory systems, multi-threading of multiple LLM processes, improved planning for multi-step reasoning, etc.)
- Development of the agent interaction loop, encompassing tool execution, parsing, and more
- R&D of LLM serving methods to improve serving agent workloads (e.g. constrained decoding and prefix caching)
- Model evaluation and finetuning, such as finetuning state-of-the-art open-weights models on agent data traces
- Writing and publishing technical blog posts and whitepapers
Preferred Qualifications
- Experience with the latest GPUs for training/finetuning
- Familiarity with model serving and API credits across frontier model providers