Mechanical Engineer for AI Model Evaluation

Apply hands-on mechanical engineering judgment to improve how advanced AI models reason through real-world engineering work. You will partner with AI research and program management teams to assess model performance, define standards for correct solutions, and create rigorous evaluations grounded in industry practice.

• Review mechanical engineering tasks and model outputs for incorrect assumptions, missing constraints, unit or tolerance errors, unsafe design choices, and responses that would not withstand a design review.
• Write clear instruction specifications, develop worked reference solutions, and create tasks that reflect practical engineering workflows.
• Design challenging benchmarks and evaluation sets spanning mechanical design, thermal and fluid systems, structural and stress analysis, manufacturing, and controls.
• Help develop domain-specific tools with the research team.
• Collaborate with researchers and adjacent-domain specialists to calibrate consistent standards and convert engineering judgment into explicit evaluation criteria.

• Bachelor''s degree or higher in Mechanical Engineering or a closely related engineering discipline.
• At least 5 years of hands-on mechanical engineering experience in industry, such as product design and development, thermal and fluid systems, HVAC, structural or stress analysis, manufacturing engineering, automotive, aerospace, energy, robotics, or medical devices.
• Experience owning real engineering work, including designing components or systems, conducting FEA or CFD analyses, releasing drawings and specifications, or leading products through design reviews, testing, and production.
• Working fluency with engineering tools such as SolidWorks, CATIA, NX, Creo, AutoCAD, ANSYS, Abaqus, or MATLAB.
• Familiarity with applicable codes and standards, including ASME, ASTM, ISO, and GD&T under ASME Y14.5.
• A record of progression toward senior or lead engineering responsibility. A Professional Engineer license is preferred but not required.
• Hands-on professional use of large language models and the ability to distinguish sound reasoning from plausible but incorrect answers.
• Excellent written communication skills and the ability to provide precise, well-structured feedback.

• Remote role open to candidates located within the United States.
• W-2 hourly employment, working within the client''s tools alongside its research teams with client-issued accounts and equipment.
• Full-time commitment of 40 hours per week.
• Initial engagement of 2 to 3 months, with potential extension based on performance and project needs.

$60 to $90 per hour.

This opportunity may be accessed through an online talent marketplace. The employer of record administers employment, onboarding, payroll, benefits, and compliance, while employees are placed directly on the client team.

Employment decisions are made without discrimination based on any legally protected characteristic, including race, religion, color, national origin, sex, pregnancy-related conditions, sexual orientation, gender identity or expression, age, veteran status, disability, genetic information, or political views or activity. Reasonable accommodations are available for qualified individuals with disabilities and disabled veterans throughout the application process.