Biophysics
Physics
AI
+12
Research
Reasoning
Auditing
MATCH
Mathematics
Dynamics
LaTeX
Python
SymPy
Jupyter
English
Education
CritPt is a public benchmark of research-level physics challenges, built to test whether frontier AI models can carry out genuine physics research reasoning rather than textbook problem solving. The benchmark paper is arXiv:2509.26574 and we recommend reading it before applying.
Dynamics
Physics
AI
+12
Research
Reasoning
Auditing
Linear
MATCH
Analysis
Mechanics
Mathematics
Engineering
Literature
LaTeX
Python
CritPt is a public benchmark of research-level physics challenges, built to test whether frontier AI models can carry out genuine physics research reasoning rather than textbook problem solving. The benchmark paper is arXiv:2509.26574 and we recommend reading it before applying.
Physics
AI
Research
+12
Reasoning
Auditing
Mathematics
MATCH
Gaussian
Index
Combinatorics
Calculus
Geometry
Analysis
LaTeX
Python
CritPt is a public benchmark of research-level physics challenges, built to test whether frontier AI models can carry out genuine physics research reasoning rather than textbook problem solving. The benchmark paper is arXiv:2509.26574 and we recommend reading it before applying.
Physics
Thermodynamics
AI
+12
Research
Reasoning
Auditing
MATCH
Index
Gaussian
Transformations
Mechanics
Algebra
Analysis
LaTeX
Python
CritPt is a public benchmark of research-level physics challenges, built to test whether frontier AI models can carry out genuine physics research reasoning rather than textbook problem solving. The benchmark paper is arXiv:2509.26574 and we recommend reading it before applying.
CritPt is a public benchmark of research-level physics challenges, built to test whether frontier AI models can carry out genuine physics research reasoning rather than textbook problem solving. The benchmark paper is arXiv:2509.26574 and we recommend reading it before applying.
Physics
AI
Research
+12
Reasoning
Auditing
MATCH
Angular
Communication
Gaussian
Dynamics
Quantization
Precision
Electron
Interference
Simulation
CritPt is a public benchmark of research-level physics challenges, built to test whether frontier AI models can carry out genuine physics research reasoning rather than textbook problem solving. The benchmark paper is arXiv:2509.26574 and we recommend reading it before applying.
Physics
AI
Research
+12
Reasoning
Auditing
MATCH
Communication
Geometry
Analysis
Index
LaTeX
Python
SymPy
Jupyter
English
CritPt is a public benchmark of research-level physics challenges, built to test whether frontier AI models can carry out genuine physics research reasoning rather than textbook problem solving. The benchmark paper is arXiv:2509.26574 and we recommend reading it before applying.
Physics
AI
Research
+12
Reasoning
Auditing
MATCH
Optics
Channels
Optimization
Probability
Calculus
Linear
Simulation
Interference
Inequality
CritPt is a public benchmark of research-level physics challenges, built to test whether frontier AI models can carry out genuine physics research reasoning rather than textbook problem solving. The benchmark paper is arXiv:2509.26574 and we recommend reading it before applying.
Physics
AI
Research
+12
Reasoning
Auditing
MATCH
Algebra
Statistics
Channels
Thermodynamics
Electron
Communication
Analysis
Geometry
Localization
CritPt is a public benchmark of research-level physics challenges, built to test whether frontier AI models can carry out genuine physics research reasoning rather than textbook problem solving. The benchmark paper is arXiv:2509.26574 and we recommend reading it before applying.
AI
Reasoning
STEM
+12
Planning
Writing
Mapping
Polish
Syntax
Algorithms
Organization
Logic
Infrastructure
Education
Annotation
Assurance
Turing is one of the world’s fastest-growing AI companies, accelerating the advancement and deployment of powerful AI systems.
Biology
AI
Reasoning
+12
Healthcare
Research
Curation
Microsoft Teams
Training
Infrastructure
Accuracy
Consistency
Mechanical Systems
Literature
Rubrics
Confidentiality
Turing’s mission is to accelerate superintelligence to drive real economic progress. Headquartered in San Francisco, Turing works with frontier AI labs to generate high-quality data, evaluations, and reinforcement learning environments that improve model capabilities in coding,…
AI
Chemistry
Chemical Safety
+12
Engineering
Pharmacology
Biochemistry
Accuracy
Calibration
Annotation
Contracts
Training
AI Safety
Organic Chemistry
Analytical Chemistry
Chemical Engineering
Pasiflora AI has immediate openings for Chemical AI Safety Annotators & Subject Matter Experts to evaluate AI-generated responses in chemistry and chemical-safety scenarios.
AI
Benchmarking
Reasoning
+12
Physics
Chemistry
Biology
Genetics
Neuroscience
Mathematics
Economics
Geology
Geophysics
Consistency
Analysis
Communication
Truelancer AI is looking for exceptional domain experts, researchers, and PhDs to contribute to an advanced AI Benchmarking Project.
Physics
Infrastructure
AI
+12
Training
Engineering
Microsoft Teams
Rubrics
Stoichiometry
Thermodynamics
Simulation
Reasoning
ROOT
Fine-Tuning
Precision
Logic
Turing is one of the world's leading AGI infrastructure companies, working with frontier AI labs to accelerate model development through high-quality training data, evaluations, and engineering talent.
AI
Reasoning
Literature
+11
Mechanical Systems
Interpretation
Biology
Research
English
Training
Make
Flexible
Life Sciences
Experimental Design
Data Interpretation
Models blur the line between what's established, what's contested, and what's simply made up in the life sciences, and they cite papers that don't exist.
Mathematics
Reasoning
AI
+8
Writing
LaTeX
English
Training
Make
Flexible
Mathematical Reasoning
Applied Mathematics
Frontier models still fail at rigorous multi-step mathematics: invalid derivations, unjustified leaps, and confidently wrong final answers. Automated checks can't grade a proof. You can.
Physics
AI
Reasoning
+8
Mechanics
Thermodynamics
Research
English
Training
Make
Flexible
Graduate-Level Physics
Models can recite physics and still get it wrong: dimensional errors, misapplied approximations, and derivations that skip the step where the physics actually happens.
Models routinely propose impossible mechanisms, unsafe procedures, and syntheses that no bench chemist would attempt. As a Chemist you'll evaluate AI chemical reasoning, catch what's wrong or unsafe, and write the answers a trained chemist would give.
Research
Engineering
Command Line
+12
Geophysics
Geology
AI
Python
Shell Scripting
Analysis
Modeling
Forecasting
Transformations
Accuracy
Metadata
Hydrology
We are seeking Earth Sciences experts to develop realistic, terminal-based scientific tasks for Terminal Bench Science. You will create computational workflows involving environmental data, climate systems, atmospheric processes, geophysics, oceanography, geology, and related…
AI
Audit
Training
+12
Reasoning
Physics
Accuracy
Logic
Engineering
English
Monday.com
Licensing
Red Teaming
Annotation
Writing
Go
Sovrano AI builds evaluation and training data for frontier AI labs, and this panel audits nuclear and radiological answers specifically. Each task gives you one user request and the answers three different models produced for it.
Biology
Spreadsheets
Accuracy
+9
English
PowerPoint
Rubrics
Environmental Science
Professional Experience
Microsoft Office
Google Workspace
Google Slides
Written Feedback
We are hiring expert Evaluators in Biology / environmental science to review and assess AI-generated work products (documents, spreadsheets, and slide decks) for accuracy, rigor, and domain quality. You will apply deep subject-matter expertise to grade outputs.
Mathematics
AI
Research
+12
Verification
Accuracy
Economics
Modeling
Programming
Optimization
Recall
Markdown
Precision
Statistics
Writing
English
We are seeking expert mathematicians to author and review high-quality academic assessment content for an AI research initiative.
Research
Microsoft Teams
AI
+12
Training
MATCH
Writing
Analysis
Interpretation
Statistics
Communication
Reasoning
Biology
Chemistry
Physics
Astronomy
The research teams behind the best-known AI models come to Mercor for scientific judgment they can't generate on their own. Your standards and expertise become the rubric that frontier AI is graded against.
The research teams behind the best-known AI models come to Mercor for mathematical judgment they can't generate on their own. Your standards and expertise become the rubric that frontier AI is graded against.
