Applied Computer Science Benchmark Specialist

This role is for one of our clients

Compensation: $66 - $84 per hour

We are seeking experienced computer science professionals to author and review high-quality academic assessment content for an AI research initiative. In this role, you will develop and validate rigorous multiple-choice questions across a broad range of computer science domains, assess solution quality, and help establish gold-standard benchmarks for evaluating advanced AI systems.

You will contribute through one of two primary task types:

Question Authoring — Develop original, challenging multiple-choice questions within your area of computer science expertise, assess their difficulty, and submit them for review.

Question Verification — Review existing questions for technical accuracy, clarity, completeness, and rigor. Make necessary edits, assess difficulty, and document the rationale behind your changes.

• Accelerator / GPU Kernel Engineering
• Formal Methods & Automated Reasoning
• Computer Architecture & Accelerators
• Distributed Systems
• DevOps & Site Reliability Engineering
• Data Engineering & Databases
• Cloud Computing & Infrastructure
• Operating Systems & Systems Kernel
• Machine Learning Engineering
• Web & API Development
• Embedded Systems Engineering
• Computer Graphics & Game Development
• Mobile Engineering

• Create original computer science questions that evaluate deep conceptual understanding, technical reasoning, and problem-solving rather than surface-level recall.
• Ensure every question is unambiguous, self-contained, technically accurate, and sufficiently specified for a qualified expert to solve.
• Classify questions by difficulty:
• Medium: Introductory undergraduate level
• Hard: Advanced undergraduate level
• Expert: Postgraduate level and above
• Provide one correct answer alongside nine plausible but subtly incorrect alternatives designed to distinguish strong technical reasoning from superficial knowledge.
• Develop clear, structured solution explanations that demonstrate the reasoning and technical principles required to reach the correct answer.
• Provide 1–5 authoritative references per question, drawing from peer-reviewed research, academic publications, university resources, and other reputable technical sources.
• For verification assignments, identify issues related to correctness, clarity, completeness, precision, or solvability and clearly explain the reasoning behind any recommended edits.
• Apply consistent standards when evaluating questions and solutions to ensure benchmark quality and reproducibility.

• PhD or doctoral candidacy in Computer Science, Electrical Engineering, Computer Engineering, or a closely related discipline.
• A Master's degree may be considered for candidates with exceptional expertise in a specialized computer science domain.
• Strong command of graduate-level computer science theory, algorithms, systems, software engineering, architecture, and/or machine learning.
• Demonstrated depth in one or more of the listed technical domains.
• Research publications, substantial industry experience at leading technology organizations, systems engineering experience, or competitive programming experience is a strong plus.
• Excellent written English and the ability to communicate complex technical concepts clearly, accurately, and concisely.
• Strong attention to detail and the ability to distinguish technically valid solutions from plausible but incorrect approaches.

• Expected commitment: 10+ hours per week
• Fully remote and asynchronous
• Flexible scheduling based on project requirements
• Opportunity to contribute to the development of high-quality benchmarks for evaluating advanced AI systems
• Strong contributors may be considered for additional review, evaluation, or subject-matter expert opportunities

Submit your resume or a summary of your relevant academic and professional background.

Selected candidates may be asked to complete a short technical assessment or provide additional information about their area of expertise.

We consider all qualified applicants without regard to legally protected characteristics and provide reasonable accommodations throughout the application and engagement process.

• Engagement will be on an independent contractor basis.
• This is a fully remote opportunity that can be completed on your own schedule.
• Projects may be extended, shortened, or concluded early depending on project requirements and performance.
• Work will not require access to confidential or proprietary information belonging to any current or former employer, client, or institution.
• Payments are made weekly through Stripe or Wise, based on services rendered.
• H-1B and STEM OPT candidates are not eligible for this opportunity at this time.