Remote Computational Chemistry & Electronic Structure Expert - AI Trainer

Overview

We are building a large-scale benchmark to test how well advanced AI systems can solve hard scientific and engineering problems. As a task designer, you will create challenging computational problems that test AI’s ability to use real scientific software for research-level work, including running simulations, interpreting results, designing experiments, and uncovering hidden information from data.

You will create problems that require skilled use of specialized scientific software. Some tasks will ask the AI to compute exact answers from a fully defined setup—testing computational accuracy. Other tasks will require the AI to plan a series of queries or experiments to uncover information that isn’t directly visible, demanding strategic measurement and efficient narrowing of possibilities. Each problem will go through a testing loop against state-of-the-art AI models, and you will refine it until it reaches the target difficulty.

• Computational Chemistry & Electronic Structure, working with PySCF for quantum chemistry calculations, including Hartree–Fock, DFT, TDDFT, CASSCF, and post‑HF methods.
• Ability to design problems around excited‑state analysis, orbital diagnostics, choosing the right method for challenging electronic structures, and interpreting computational artifacts that arise from method limitations.
• Experience with other specialized software in this domain is also considered.

You have graduate-level expertise (MS or PhD preferred) in the domain above, with real hands‑on experience using these tools—not just theoretical knowledge. You have written code using these libraries to solve actual research problems, and you understand their limitations, edge cases, and what makes a problem genuinely hard. You think like a puzzle designer, building problems whose challenge comes from smart reasoning rather than raw computation.

• Graduate‑level training in a relevant STEM field (MS, PhD, or equivalent research experience).
• Proven proficiency with at least one of the listed scientific software libraries, shown through research publications, open‑source contributions, or professional work.
• Strong Python skills – you will write problem setups, oracle functions, and solution validators.
• Ability to work independently and refine problem designs based on feedback.
• Comfortable working in a Linux/terminal environment with remote compute sandboxes.
• Available for at least 15–20 hours per week.

• Experience across multiple listed domains or tools.
• Familiarity with benchmark or evaluation design.
• Background in scientific teaching or exam/problem‑set design.
• Experience with computational reproducibility and containerized environments.