Member of Technical Staff (Agent Infrastructure & Research)
About ArettaOur mission is to make AI provably trustworthy, starting with the world’s software.
AI is about to write the world’s software. All of it, from the critical infrastructure everything depends on to the apps people use every day. We want a future where people decide what software should do and machines prove that it does. We’re starting with the tools engineers need to ship AI-written code knowing it’s correct.
Within six months of starting, we're deployed with paying design partners in databases and data infrastructure, where we've found 60+ critical bugs, including data-loss bugs that survived their testing and simulation stacks. We're backed by visionaries like Ion Stoica, Kurt Keutzer, Sanjit Seshia, Ram Shriram and Sriram Rajamani. The founders, Sushant and Adwait, were previously PhD and postdoc at UC Berkeley.
Soon agents will do most of the work of building software, and nobody has figured out the infrastructure that makes that work at scale. We have to, and at a scale few others face: our agents work across every codebase we support and verify, for many organizations at once, not one team’s repository. That makes this part engineering and part frontier research. You’ll build the platform those agents run on: which models handle what, what context each agent sees, how the system learns from every run, and how people see and trust what the agents did. If you want to define how the next generation of software gets built, this is where to do it.
Problems you’d own
Route work to the right model. Decide which model handles which task, at what cost and speed, and measure whether the choice was right.
Give agents the right context. Build retrieval, memory and context compression so agents see what matters and nothing that doesn’t.
Build evals that point the way. Design evals that tell us what to improve next, and show whether a change actually made the agents better.
Make it all visible. Build observability that shows what every agent did, why, and what it cost, so engineers can trust it and debug it.
Make the system learn continuously. Use the trajectories from every run to improve the system automatically: new skills and tools, cheaper distilled behavior, and fixes for failures we keep seeing.
Rethink code for agents. Design how code, proofs and their history are represented, stored and versioned when agents write most of them.
You don’t need to have done all of this. We care about how you’d approach it.
You might be a fit if
You’ve built agent systems that run in production, not just demos. You trust evals more than impressions, and you can tell when an agent is actually getting better. You’re comfortable across models, infrastructure and product, and you move fast without losing track of cost and correctness.
You don’t need
A background in formal methods. We’ll teach you.
A machine learning research background or a PhD.
Bonus points
Agents: you’ve built agent harnesses or coding agents.
Scale: you’ve worked on model routing, evaluation or observability at scale.
Developer infrastructure: you’ve worked on version control, build systems or other developer infrastructure.
Who we hire
We hire at every level, and we mean it. If you’re senior, you’ll come in as a hands-on engineer and grow into leading and building a team. If you’re early in your career, fresh out of school or a few years in, you’ll get real ownership fast and as much scope as you can take on. What matters is the same bar for everyone: mastery, the drive to grow, and the instinct to help others grow too.
Compensation and logistics
Benefits: unlimited PTO, health, dental and vision insurance, and a 401(k).
How we work
We work in roughly six-week cycles: five intense weeks, then a week for reflection, polish, feedback and mentorship. We bring opinionated ideas backed by evidence, bias for action, fix the class of problem rather than the instance, and close the loop with the people we serve. Read more in Our Culture.
Aretta comes from aretē, the Greek word for excellence and virtue: becoming the best version of yourself in everything you do. We value excellence for its own sake, and we believe it’s built across a whole life, not just the hours at a desk.
We work in person in the San Francisco Bay Area. For the right person we’ll consider remote, so don’t let location stop you from applying.
Our hiring process is probably unlike any you've been through, so please read about it before you apply. Everyone joins Aretta the same way: No puzzles, no whiteboards, and the process typically takes about a week end to end (subject to scheduling availability). You share real work you've done, then we spend a few hours on a real problem together to get a mutual feel for working side by side. Learn more here: How We Hire.