Materials Science Expert - Engineering

Obsidian; Mumbai; On-site; INR 1,800,000 - 3,000,000; Full time

Job summary

Obsidian is seeking a senior professional to design and run evaluation tasks that test AI models against expert-level work in materials science or electrical/mechanical engineering. You will craft prompts, data rooms, and grading schemes to produce objective measurements of model performance.

The role involves shaping undefined work streams, collaborating with domain experts, and iterating on criteria to clearly distinguish good vs. suboptimal model reasoning.

Qualifications

• Senior expertise in materials science or in electrical/mechanical engineering.
• Ability to navigate ambiguity and shape undefined work streams.
• Ability to explain why an answer is right or wrong.

Responsibilities

• Author domain-authentic tasks drawn from your work.
• Build data room and grading criteria to ensure objectivity.
• Run tasks on models and analyze performance to discriminate.
• Collaborate with project lead and domain experts to define success criteria.

Skills

Materials science

Electrical engineering

Mechanical engineering

Additive manufacturing

CFD/Fluids

NDE/CAE

Job description

About the role

We build materials-science and engineering tasks that test how well an AI model does real expert work. You write a realistic task — a prompt, a data room, and a way to grade it — run it against the model, and tighten it until the model can no longer reason through it cleanly.

What you'll do

• Author domain-authentic tasks drawn from work you've actually done.
• Build the data room and grading criteria that make the task objectively scorable.
• Run the task against the model, analyse where it succeeds or fails, and iterate until it genuinely discriminates.
• Work with the project lead and other domain experts to settle what "good" looks like in your domain.

Who we're looking for

• Senior expertise in materials science — metals, ceramics, composites, characterization, additive manufacturing — or in electrical engineering (analog, RF, power) or mechanical engineering (design, CFD and fluids, heat transfer, pressure vessels, NDE, CAE).
• Comfortable navigating ambiguity — much of the work is still being defined, and shaping it is part of the role.
• Able to explain not just the right answer, but why a wrong answer is wrong.

Support

Daily onboarding sessions and multiple office hours every day.