Remote Computer Science Expert for AI Model Evaluation

About the role

Turing is seeking PhD‑level computer science experts to design and evaluate challenging problems that probe the reasoning abilities of large language models such as ChatGPT. The work is fully remote and focuses on creating conceptual, high‑impact benchmarks across core CS domains.

Key responsibilities

• Design advanced computer‑science problems that test AI performance in algorithms, systems design, cybersecurity, theory, databases, networks and related areas.
• Develop clear, step‑by‑step reference solutions with rigorous logic and well‑structured explanations.
• Evaluate AI‑generated responses for correctness, reasoning quality, completeness, clarity and alignment with problem requirements.
• Identify flaws, edge cases and near‑miss reasoning patterns in model outputs.
• Collaborate with researchers to refine benchmarks for undergraduate, graduate and PhD‑level topics.
• Provide structured feedback to improve problem quality, benchmark reliability and evaluation standards.

Required profile

• PhD (completed or in progress) in Computer Science or a closely related field.
• Strong analytical and problem‑solving skills across advanced CS domains.
• Ability to craft conceptual problems that require deep understanding rather than simple recall.
• Excellent written communication with a focus on clear, logical explanations.
• Meticulous attention to detail when evaluating reasoning, assumptions and edge cases.
• No prior AI experience required.

Required skills

• Algorithms
• Systems design
• Cybersecurity
• Theoretical computer science
• Database concepts
• Network concepts

What we offer

• Contract engagement with flexible hours (minimum 4 h/day, up to 40 h/week).
• Remote work with a 4‑hour overlap with Pacific Standard Time.
• Opportunity to influence cutting‑edge AI research and enterprise applications.