Solving Self-Improving Superintelligence

The human brain is a sponge. Today’s AI brains are brittle and rigid. At Letta, we’re building self-improving artificial intelligence: creating agents that continually learn from experience and adapt over time.

Founded by the creators of MemGPT from UC Berkeley’s Sky Computing Lab (the birthplace of Spark and Ray). Backed by Jeff Dean, Clem Delangue, and pioneers across AI infrastructure. Our agents already power production systems at companies like 11x and BILT Rewards, learning and improving every day.

We’re assembling a world-class team of researchers and engineers to solve AI’s hardest problem: making machines that can reason, remember, and learn the way humans do.

Note that this role is in-person (no hybrid), 5 days a week in downtown San Francisco.

Your role

You'll develop the foundational methods that enable AI systems to learn and self-improve over time. This means tackling the core research challenges around memory, context management, and agent architectures that allow AI systems driven by large language models to evolve through experience - moving us closer to agents with human-like (and beyond human) learning capabilities.

At Letta, you’ll work with a world-class, tight-knit team of AI researchers and engineers towards our vision of self-improving superintelligence.

Core Research Areas

Memory & Learning Systems

• Design novel memory systems that enable agents to learn from interactions and improve over time, learning both in weights (parametric memory) and in learned context (non-parameteric memory, or “system prompt learning”)

• Develop context management techniques that solve the long context / context derailment problem

Agent Architectures

• Advance state-of-the-art in stateful agent systems and self-improvement mechanisms

• Research multi-agent coordination and knowledge sharing between learning agents (multi-agent shared memory)

• Develop evaluation frameworks for measuring learning and adaptation in AI systems

• Pioneer new approaches to agent reasoning, planning, and decision-making over extended time horizons

Open Research & Impact

• Advance the field through open publishing of research through papers, technical reports, blog posts, and open source code

• Collaborate with the broader research community on fundamental problems in self-improvement and continual learning

What We're Looking For

• Deep expertise in machine learning, particularly in LLMs, continual learning, and/or LLM agent architectures

• Track record of impactful research (breakthrough publications and/or open source contributions)

• Desire for real-world impact beyond pure academic work

• Drive to solve AI's hardest problem

Our culture

Signs it could be a great fit:

• You want to be an integral part of turning a tiny startup into a trillion dollar company. You wonder what it would have been like to be at OpenAI when it was just a dozen people, or Google when it was just a couple grad students in a garage.

• If you work / worked at a large tech company: you felt physically pained by the red tape and bureaucracy wedged between you and your potential impact.

• You’re excited to go head-to-head with tech giants, frontier labs, and other startups that are many times our size in both headcount and funding.

• You are anti closed frontier AI that is controlled by a few private tech companies.

Signs it’s a bad fit:

• You like having things planned out far ahead of time, and get stressed out when there’s nobody telling you exactly what to do. We look for people that thrive in ambiguity and can drive their own agenda.

• You want to work a 9-5, and value clear separation of work from life. The stakes are high, and the only moat is execution and velocity. We work hard because incredible outcomes require incredible sacrifice – operating on a strict 9-5 guarantees failure.

• You value titles or want to people-manage. Letta is a flat company where every researcher and engineer is an individual contributor.

• You’re not interested in talking to customers, and prefer to stick to one part of the stack. At Letta everyone on the team engages directly with our customers and works across the stack.

Our Interview Process:

• Initial screen (30 min)

• Technical screen (1-1.5 hours)

• Paid in-person work trial (2 days onsite in SF)