Remote AI Mech Eng Task Designer & Evaluator

Planet Pharma; San Francisco (CA); Remote; USD 90,000 - 150,000; Part time

Job summary

Planet Pharma seeks an experienced mechanical engineer to design realistic, practice-driven tasks for evaluating frontier AI models. You will craft prompts, select drawings and data, and oversee evaluation against professional standards.

Remote work is supported and tasks emphasize real-world judgment and detailed written reasoning. The role requires 2+ years in mechanical engineering, strong CAD/FEA knowledge, and excellent English communication.

Qualifications

• 2+ years of professional mechanical engineering experience.
• Fluent written and spoken English.
• Meticulous attention to detail and strong problem solving.

Responsibilities

• Design challenging, realistic mechanical engineering tasks drawn from your own day-to-day work; create prompts, files, and data needed.
• Run tasks through frontier AI models and evaluate against professional standards.
• Compare model outputs on identical prompts and files; document which performed better and why.
• Write closed-ended problems with worked solutions and grading rubrics; specify correct deliverables and acceptance criteria.
• Flag concrete failures with evidence: boundary conditions, unit errors, interferences, tolerance issues, unsafe factors of safety.

Skills

Experience

English proficiency

Attention to detail

Self-direction

Education

Bachelor's in mechanical engineering or related

Tools

CAD software

FEA/CFD

MATLAB/Python

Job description

Planet Pharma seeks an experienced mechanical engineer to design realistic, practice-driven tasks for evaluating frontier AI models. You will craft prompts, select drawings and data, and oversee evaluation against professional standards.

Remote work is supported and tasks emphasize real-world judgment and detailed written reasoning. The role requires 2+ years in mechanical engineering, strong CAD/FEA knowledge, and excellent English communication.