About us
We're reverse-engineering the origin of life — one of the great unsolved problems in science, and one we think AI finally makes tractable. Understanding this transition, from geochemistry to biochemistry, is what will let us orchestrate molecular networks and build systems that are more capable, adaptive, and efficient.
If we succeed, the applications are vast: catalysis, green synthesis, ab initio synthetic biology, programmable matter. Understanding and harnessing these processes could let ten billion of us thrive on this planet — and let life keep evolving beyond it.
We're a small, diverse team of AI engineers, computational scientists, and bench scientists. We hold ourselves to the rigor of a research institute, but we ship like an engineering firm. Global team, HQs in Cambridge, MA and London, UK.
The role
You'll simulate enzyme-catalysed reactions from the physics up. Using reactive and free-energy methods you'll map how reactions proceed in the active site, compute transition states and barriers, and work out where the catalysis actually comes from: why a step has the barrier it does, which residues do the work, and how mutations move it. You'll work with the wider simulation and ML teams, but also directly with our bench scientists — seeing your predictions tested in vitro and getting experimental feedback on fast, tight loops.
What you'll do
Characterise mechanisms, transition states, and activation barriers in the active site, and compare computed barriers against measured kinetics
Pin down the origins of catalysis — the residues, interactions, and dynamics that set rate and selectivity — and use MD to understand how active-site motion shapes the reaction
Turn results into concrete, testable proposals for the wet lab, and fold the resulting data back into your models
Help physics-based and learned methods strengthen each other as we build them out
Essential experience.
Expertise in enzymatic reaction modelling using QM/MM and a variety of free energy methods
A solid grasp of enzyme catalysis: mechanism, kinetics, cofactors, and how active-site chemistry and conformational dynamics sets rate and selectivity
Sound judgement about method selection, good understanding o methodological limitations and computational cost
Highly preferred
Experience in protein design for enzymatic optimization
You've run design–test–refine cycles with a wet lab before
Experience with reactive machine-learned potentials, or coupling physics-based modelling with ML
Logistics
Compensation is highly competitive. We're also able to sponsor visas for the right candidate.