Senior Materials Scientist for GenAI Benchmarks Bay Area

Mercor; New York (NY); Hybrid; USD 180,000 - 230,000; Full time

Job summary

Cincinnatus LLC provides W-2 employment and places professionals with leading AI labs. This senior materials science role focuses on QA, instruction specs, and benchmark creation for frontier AI models in materials science.

Hybrid Bay Area positioning requires on-site work several days weekly, with relocation if needed at the candidate's cost. Ideal candidates have a PhD in materials fields, 4+ years of R&D, and strong AI fluency to translate tacit judgment into explicit criteria.

Qualifications

• PhD in materials science, materials engineering, or closely related discipline.
• 4+ years of substantive research or industrial R&D in materials disciplines.
• Genuine specialization in at least one materials domain.
• Senior level with ownership of research direction.
• Peer-reviewed publications, patents, or shipped materials programs preferred.
• Hands-on AI fluency with large language models in professional work.

Responsibilities

• Data QA and reviews of materials science knowledge work tasks and model outputs.
• Write instruction specs and golden solutions for materials problems; define new tasks.
• Design challenging materials science tasks and evaluation sets for domain depth.
• Coordinate calibration with client researchers to ensure consistent standards.

Skills

Data QA

Instruction writing

Benchmark design

Calibration

Written communication

Relocation willingness

Education

PhD in materials science or closely related

Master's with exceptional industrial depth

Job description

Cincinnatus LLC provides W-2 employment and places professionals with leading AI labs. This senior materials science role focuses on QA, instruction specs, and benchmark creation for frontier AI models in materials science.

Hybrid Bay Area positioning requires on-site work several days weekly, with relocation if needed at the candidate's cost. Ideal candidates have a PhD in materials fields, 4+ years of R&D, and strong AI fluency to translate tacit judgment into explicit criteria.