Logo
Letta Cloud

Founding Product Engineer

Letta Cloud, San Francisco, CA, United States


Our background

Letta is a company founded around the MemGPT project (12k+ GitHub stars). The founding team comes from the same research lab and PhD advisors at Berkeley that produced Spark (→ Databricks) and Ray (→ Anyscale). We have deep expertise in both AI and systems, are currently hiring a founding team of exceptional engineers to join us in building the next generation of LLM agent technology.

Your role

Our goal as a company is to empower developers to build state-of-the-art LLM agents to power their own applications. As a Product Engineer, you will:

  • Lead development of a web platform for developers that are designing, debugging, and deploying LLM agents.

  • Play a crucial role in building a developer experience around technology that allows agent builders to observe and control agent behavior at a much deeper level, while also working with a design team and LLM researchers.

  • You should have a fascination with LLM technology, as this role will require interacting closely with LLMs and understanding how to provide the human interfaces that allow developers to push LLMs to their limits.

Your skillset

You’re an ideal candidate for this position if:

  • You have a deep familiarity with the modern web stack

    • React is your bread and butter - you’ve been writing React professionally for 3+ years

    • Keywords: React, Typescript, Tailwind, Nx, TanStack, Radix UI, Zod, Zustand

  • You know how to work with designers

    • You’ll be working closely with our design team to build the UI/UX

    • Keyword: Figma

  • You are fluent in Python and know your way around a REST API server

    • You’ll also be working closely with the LLM research team to develop new APIs and schemas for agents

    • Keywords: Python, FastAPI

  • You’ve built an LLM chatbot frontend before

    • OpenAI playground, but for Ollama? You could mock that up in a day or two

    • Token streaming over POST SSE? No problem

  • You are fascinated by LLM technology

    • Even if you don’t have a formal background in LLMs, you love keeping up to date with the latest in LLM technology (your laptop is loaded with llama.cpp and 1TB of model weights)

    • You love learning about how agents and LLMs work under the hood

  • You love beautiful things (you’ve made them before, and can show us)

    • And by “things” we mean web apps

    • And by “beautiful”, we mean it looks like something on @shadcn’s timeline

    • Portfolio projects (either OSS or live websites) that we can look at are a major plus

Our hiring process

We are hiring a small, tight-knit team of exceptionally talented founding engineers. Every hire matters, so we take the hiring process very seriously.

  1. Initial phone interview (30m video call): We want to learn more about your background, your skills, your opinions on open source AI, and why you want to work at an early stage AI startup.

  2. Technical take-home (<1hr assessment): To get a better sense of your skillset, we’ll give you an example problem to work that’s as targeted to your potential day-to-day work as possible.

  3. Paid workday (in-person recommended): As the final step in the interview process, we’ll simulate working together as closely as possible by giving you a real (or as close to real as possible) task to work on for a day - and paying for your time of course. If you live in the Bay Area, we highly recommend visiting our offices in-person! We’re an in-person company, so working at our office will give you a great idea of what it will be like to join as a full-time member of the team.

#J-18808-Ljbffr