Mechanical Engineering Task Developer

As a Mechanical / Industrial Engineering Expert, you will collaborate with leading AI labs to enhance frontier agent evaluations in mechanical engineering. Your primary responsibility will be to create long-horizon engineering tasks that reflect real-world engineering work, each accompanied by a deterministic rubric to assess agent performance against verifiable ground truth.

• Develop scenarios for:
• Design review: Verify drawings and GD&T against a defect list, and check CAD models against specified dimensions.
• Analysis: Conduct tolerance stack-ups with computable results and perform DFM/DFA reviews against a defined checklist.
• Change management: Create ECOs with required fields and ensure BOMs match a target structure.
• Engage in challenging tasks that require long sessions of focused work.

• BS or MS in Mechanical, Industrial, or Manufacturing Engineering.
• 3+ years of experience in design, manufacturing engineering, or product development.
• Expertise in one or more of the following: CAD systems (SolidWorks, Creo, NX, CATIA, Fusion 360), GD&T, PLM systems (Arena, Teamcenter, Windchill), or specific manufacturing processes (machining, injection, sheet metal, additive).
• Ability to read and produce mechanical artifacts, including 2D drawings, BOMs, tolerance analyses, ECOs, and DFM reviews.
• Strong written communication skills, with the ability to articulate reasoning step by step and encode it into deterministic rubrics.
• Must be located in the United States or Canada.

This is a remote position with an hourly employment type.

Compensation ranges from $75 to $100 per hour, depending on domain depth and prior experience. Strong contributors will have opportunities for promotion based on task quality and throughput.