almost 2 years ago
Responsibilities
- Develop Letta’s open-source agents framework and cloud service.
- Design scalable and resilient backend services and APIs for Letta Cloud.
- Work with researchers to support cutting-edge agent architectures.
Requirements
- Strong proficiency with Python.
- Strong understanding of architecting services for security, reliability, and performance.
- Ability to build scalable backend services.
- Strong understanding of SQL databases, particularly Postgres.
- Familiarity with AI-stack tooling, including inference engines such as vLLM and Ollama and LLM provider APIs including OpenAI and Anthropic.
- Proficiency with TypeScript, React, and Tailwind is a bonus.
- The role is for an individual contributor rather than a people manager.
- Candidates should be comfortable working in ambiguity and on a small, high-impact team.
Benefits
- In-person role in downtown San Francisco, five days per week with no hybrid option.
- Paid two-day in-person work trial onsite in San Francisco.
Tech Stack
Categories
About Letta
Today's AI agents struggle with fragmented context and limited memory. Just as computers needed operating systems to manage resources, your agents need intelligent context management to unlock their full potential. Letta is a complete operating system for building stateful agents AI agents. Letta handles state persistence, context compilation, and intelligent resource allocation, so you can focus on building applications powered by agents that actually learn. Letta was founded by the creators of MemGPT, which introduced memory (or context) management for AI agents. The company was spun out of the UC Berkeley Sky Computing research lab, and is advised by Ion Stoica (co-founder of Databricks, Anyscale) and funded by top-tier investors.