Natural Sciences and Engineering Expert (PhD or 5+ Years), AI Agent Evaluation

What you'll do: You'll take problems from your own work and turn each one into a self-contained task that an AI agent has to solve in a Linux terminal. For every task, you'll do four things: Write a clear brief. Set up the environment with the files and tools the agent needs. Build a reference solution. Write automated checks on the final result. The strongest tasks are the ones today's best agents still get wrong. Your firsthand knowledge of where real science or engineering work goes wrong is what makes them valuable. That might be a unit conversion buried in a simulation config, an alignment run against the wrong genome build, a numerical solver that quietly loses precision, or a proof step that doesn't hold. Specialties we're looking for If your background is in the natural sciences and engineering, there's likely a place for you. We're building depth across: Biology: molecular and cell biology, genomics, bioinformatics, neuroscience, and computational biology Chemistry: computational and physical chemistry, cheminformatics, and materials Physics: computational, condensed matter, and particle physics, and astrophysics Earth sciences: climate science, geoscience, remote sensing, and GISRobotics: control, motion planning, perception, and simulation Math: applied math, numerical methods, statistics, and formal proofs Linguistics: computational linguistics, phonetics, and corpus analysis Who we're looking for Academics and practitioners are equally welcome. No AI or machine-learning background is needed. We're after your science or engineering expertise and your comfort working in a terminal.