Senior Mechanical Engineer & AI Benchmark Problem Designer

Mercor; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Obsidian seeks a senior mechanical engineering expert to craft challenging industry-grounded problems, author comprehensive expert-level solutions, and validate difficulty across leading AI models. Candidates should hold a PhD in Mechanical Engineering with 8+ years of hands-on design, analysis, or R&D experience, preferably from blue-chip employers.

The role emphasizes rigorous problem creation and validation against frontier language models to ensure substantial difficulty for AI systems.

Qualifications

• PhD is required.
• 8+ years hands-on design, analysis, or R&D experience.
• Experience with blue-chip employers preferred.

Responsibilities

• Author original, free-response engineering problems grounded in real industry scenarios.
• Write a complete expert-level solution for each problem.
• Validate difficulty by running it against frontier language models until at least one fails.

Skills

Mechanical engineering expertise

Education

PhD in Mechanical Engineering

Job description

Obsidian seeks a senior mechanical engineering expert to craft challenging industry-grounded problems, author comprehensive expert-level solutions, and validate difficulty across leading AI models. Candidates should hold a PhD in Mechanical Engineering with 8+ years of hands-on design, analysis, or R&D experience, preferably from blue-chip employers.

The role emphasizes rigorous problem creation and validation against frontier language models to ensure substantial difficulty for AI systems.