Remote STEM Researcher – AI Evaluation Specialist

About the role

We are seeking a highly qualified STEM researcher to work remotely on designing and solving challenging problems that probe the limits of large language models (LLMs). The role involves creating step‑by‑step solutions with clear reasoning and contributing to the development of new evaluation benchmarks across physics curricula from early undergraduate to PhD level.

Key responsibilities

• Design and solve advanced STEM problems to test LLM capabilities.
• Produce high‑quality, detailed solutions with well‑articulated reasoning.
• Collaborate with LLM researchers to align problem sets with evaluation goals, focusing on abstraction, multi‑step reasoning, and symbolic manipulation.
• Help define and implement new benchmarks based on physics topics ranging from undergraduate to doctoral studies.
• Leverage AI tools to enhance analytical workflows and support future‑proof career growth.

Required profile

• Strong analytical background in STEM at the level of engineering entrance exams, graduate studies, or PhD research.
• Ability to break down complex concepts into clear, simple explanations.
• Creative and lateral thinking to address novel challenges.
• Excellent structured communication and collaboration skills in a remote environment.
• Self‑motivated, independent worker with reliable desktop/laptop and internet connection.

Required skills

What we offer

• Competitive compensation based on experience.
• Opportunity to work with a global leader in technology and AI.
• Fully remote work‑from‑anywhere arrangement.
• Impactful contributions to cutting‑edge AI evaluation research.