Our background

Letta is a company founded around the MemGPT project (10k+ 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.

Note: This is a senior role. Engineers with a more junior background should consider our other software engineer opening: Software Engineer (Founding)

Your role

As our Staff Software Engineer you will serve to balance the chaos of bleeding-edge creation of LLM agents (see our our underlying research) with the reliability and order of stable, enterprise-grade software design to enable adoption of these technologies in real systems. You will help us avoid re-inventing the wheel when classic software engineering solutions are called for, and act as an advisor when we do need to find novel solutions to novel problems. You will draw on your extensive experience with organizations of different sizes and at different stages of growth to prioritize what matters today, while being prepared for what will matter tomorrow. You will relentlessly refactor and PR review the codebase, shipping 9’s of reliability the way Oprah gives away cars. You are a teacher, and will better our software not just by writing code but by continually mentoring, reviewing, and guiding the whole team to become better at the craft of software engineering. You are not satisfied with being a spectator in the evolution of artificial intelligence, and want to be a hands-on contributor with us.

Qualifications

• You have a diverse and extensive software development career under your belt. This diversity includes:

  • Companies:

    • A variety of company sizes, industries, and growth stages

    • At least one company that has experienced startup-type growth during your tenure

    • At least one early-stage startup

  • Roles:

    • A variety of disciplines, or generalist roles with very different challenges

    • A range of team sizes and cultures

    • A variety of roles within teams (engineer, lead, manager)

  • Tools:

    • Supported, added to, and expanded on a variety of frameworks, programming languages, and design patterns

    • Multiple clouds

    • A wide range of 3rd party vendor integrations

  • Challenges: Be able to speak to a number of completely different engineering problems you have helped solve. From new features, to replatforms, to scalability issues, to technical debt, you should have enough war stories to fill a podcast

• You are a seasoned refactoring veteran. You probably fall asleep with a dog-eared copy of Martin Fowler’s Refactoring under your pillow.

• You are humble, but stand behind your “strong opinions loosely held.” MemGPT development comes from experimental and cutting edge scientific research, not classical software engineering. You communicate and teach, never lecture or scold, but you are not afraid to express strong thought leadership in software design when it is called for.

• You believe “shipping solves”, and you ship accordingly. You have the experience to shut down bikeshedding and lead our team to deliver what we’ve promised, when we promised it - no excuses.

• You are not afraid of AI. You don’t need to be an expert in RAG or logprobs filtering, but you cannot do this job effectively if you think of AI as a black box of “nerdy stuff.” Be willing to learn and understand, and allow your knowledge of software engineering to be a force multiplier for our knowledge of generative AI.

• You have significant experience maintaining Open Source Software projects. Your Github should reflect this. OSS adds unique challenges to software design and you need to have tackled them before.

• You love Python. We are a Python shop and it is going to be hard for you to hit the ground running if this is not your language of choice.

• You have enterprise experience. Words like SOC2, GDPR and HIPAA do not scare you. You’ve been down this road before and can speak to them extensively.

• You want to code. This seems obvious, but we are a young company and need a doer, not just a thinker.

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.