Senior Research Scientist - Simplex

Astera Institute•Emeryville, CA

About The Position

At Simplex, we're building a science of intelligence. Our aim is to develop and apply a rigorous theory of latent internal structure in neural networks, and how that structure relates to computation and behavior. We believe that when dealing with intelligence, understanding is safety. Without genuine understanding, we can't reliably monitor, control, or even reason clearly about what these systems are doing. But these same systems also present us with a new opportunity. For the first time, we have AI complex enough to serve as testbeds for theories of intelligence, including biological. We aim to build a theory applicable to intelligence, both artificial and biological. We have the beginnings of such a theory, grounded in the physics of information and experimentally verified in transformers. Now, we are scaling our team. Some of the near-term goals we have are building unsupervised methods that recover belief geometries in real LLMs, extending the theory to more complex cognitive tasks, and pushing toward tools reliable enough to matter for safety. This is a senior position on a small team. We're looking for someone who will shape the direction of our research, not just execute within it. That means identifying the most important open questions, designing the experiments and theory to address them, and driving projects from conception through to results that move the field. You'll work closely with the rest of the team. We do our best work when thinking together, and the best ideas here tend to emerge from conversation. But you'll also be expected to carry significant research threads independently, direct more junior researchers, and take a leadership role in figuring out what Simplex should be working on next. We are also hiring for Research Scientist positions. We're looking for people who can do rigorous mathematics and get their hands dirty with real models and data; ideally someone who moves naturally between theory and experiment, and feels deeply driven to understand intelligence. You learn across fields. Our work draws on many fields, like dynamical systems, probability, deep learning, physics, information theory, and neuroscience. You don't need to know all of it coming in, but you're the kind of person who picks things up, and follows your curiosity—and surprising experimental results—wherever they lead. You have taste. You know the difference between a problem that matters and a problem that's merely publishable. You have strong opinions about research directions, not just techniques. You've developed these opinions through experience. You’ve seen enough research programs succeed and fail to have real judgement about what’s worth pursuing, and how. You set directions. You identify which problems are worth solving. You've led research efforts before, and you've developed the instinct for when to push harder on a path and when to change course. You communicate. You can explain your ideas clearly to collaborators, in writing, and on a whiteboard. You can also explain them to people outside of your subfield. Science is a team activity for us, and at a senior level that means helping others think more clearly, not just thinking clearly yourself. You build. You're at home in front of a whiteboard and in a terminal. We are building new theory, new code, and new experiments. You think big, but you're serious about it, and you actually try to make things happen rather than just ideating. You use AI tools, you tinker, you're excited about what's becoming possible. You have a body of work that demonstrates depth and originality in a quantitative field such as physics, mathematics, neuroscience, machine learning, etc. A PhD is typical but not required if you've found another way to show this type of track record.

Requirements

Experience in a quantitative field such as physics, mathematics, neuroscience, machine learning, etc.
A body of work that demonstrates depth and originality
Ability to do rigorous mathematics and get their hands dirty with real models and data
Move naturally between theory and experiment
Feels deeply driven to understand intelligence
Learn across fields like dynamical systems, probability, deep learning, physics, information theory, and neuroscience
Know the difference between a problem that matters and a problem that's merely publishable
Have strong opinions about research directions, not just techniques
Identify which problems are worth solving
Explain your ideas clearly to collaborators, in writing, and on a whiteboard
Be at home in front of a whiteboard and in a terminal
Build new theory, new code, and new experiments
Use AI tools, tinker, be excited about what's becoming possible