Remote Pod Lead - Chemistry

Turing

1d•Remote

About The Position

Turing is seeking an experienced chemistry expert to lead a pod of trainers building realistic, terminal-based scientific tasks for Terminal Bench Science. The Pod Lead reviews every task produced by the trainers for chemical correctness, reproducibility, safety, and grader reliability, and coaches trainers to deliver consistently high-quality, challenging tasks. The role includes reviewing task statements, molecular structures, spectra, datasets, force-field parameters, environments, reference solutions, and automated tests. The Pod Lead verifies that tasks reflect authentic chemistry research workflows and require genuine multi-step reasoning, checks that software and methodological dependencies are pinned, validates chemical and computational details, and ensures results are reproducible. The role also covers grader quality, prevention of task-gaming, safety screening, actionable feedback and revision tracking, trainer onboarding and mentoring, workload allocation, throughput and quality tracking, blocker escalation, and maintaining pod documentation. The assignment requires at least four hours per day and a minimum of 40 hours per week, including four hours of overlap with PST. It is a four-week contractor assignment, with an expected start date stated as next week. The assignment does not include medical or paid leave.

Requirements

Ph.D., postdoctoral experience, or equivalent advanced experience in chemistry or a closely related field.
Strong programming skills in Python, C/C++, Julia, or Fortran, with Linux and terminal proficiency.
Hands-on experience with computational chemistry, molecular simulation, cheminformatics, or chemical data analysis.
Proven experience reviewing code, analyses, manuscripts, or research outputs.
Experience mentoring or leading small technical or research teams.
Excellent written communication skills for providing precise, constructive feedback.
Commit to at least four hours per day and a minimum of 40 hours per week, with four hours of overlap with PST.

Nice To Haves

Familiarity with PySCF, Psi4, ORCA, xTB, CP2K, NWChem, GROMACS, OpenMM, AmberTools, RDKit, Open Babel, ASE, or MDAnalysis.
Experience with free-energy methods, reaction mechanism analysis, machine-learned potentials, or spectroscopy simulation.
Familiarity with Docker, Git, CI systems, automated testing, and HPC environments.
Experience designing benchmarks, programming tasks, or simulation-based evaluations.

Responsibilities

Review trainer tasks end to end, including task statements, molecular structures, spectra and datasets, force-field parameters, environments, reference solutions, and automated tests.
Verify that tasks reflect authentic chemistry research workflows and require genuine multi-step reasoning rather than a single library call or lookup.
Check that software versions, force fields, basis sets, functionals, and dependencies are pinned and that results are reproducible.
Validate chemical correctness, including units, charge and spin multiplicity, stereochemistry and tautomer handling, method specifications, convergence, frequency checks, equilibration, and sampling adequacy.
Ensure tolerances account for method-dependent, numerical, and stochastic variation without accepting chemically incorrect results.
Ensure graders verify scientific results such as energies, geometries, thermodynamic quantities, rate constants, spectral assignments, or molecular properties rather than formatting.
Ensure tasks cannot be gamed through hard-coded outputs, reading test files, or bypassing the intended computation.
Screen tasks for chemical safety and dual-use concerns, and escalate content involving synthesis or enhancement of hazardous, toxic, or controlled substances.
Provide clear, actionable written feedback and track revisions through closure.
Onboard and mentor trainers on task design standards, common pitfalls, and grader design.
Allocate work across the pod and track throughput and quality metrics.
Escalate blockers.
Maintain pod documentation covering guidelines, recurring issues, and exemplary tasks.