Frontier AI Benchmark Researcher — Remote

Synthires; United States; Remote; USD 193,000 - 207,000; Full time

Benefits offered by this job

Fully remote opportunity

Flexible workload (5–40 hours/week)

Fully asynchronous work environment

Job summary

AfterQuery is seeking experienced Machine Learning Research Experts with a strong research track record to design benchmark tasks, evaluate model capabilities, and contribute expert-level ML reasoning to next-generation AI systems. The role emphasizes designing rigorous evaluation tasks and may focus on areas such as Language Models, Deep Learning, RL, CV, Generative AI, and more.

Fully remote, rolling applications, and asynchronous work are offered.

Qualifications

• At least one first-author research publication in ML/AI or a closely related field.
• Master's or PhD in Machine Learning, Computer Science, Statistics, Mathematics, or related quantitative discipline (completed or in progress).
• Minimum 1 year of hands-on machine learning research experience.
• Strong experience developing, training, evaluating, or deploying ML models.
• Proficiency in ML programming and experimentation.
• Ability to design rigorous research problems and evaluation frameworks.
• Excellent written communication and technical documentation skills.

Responsibilities

• Design realistic ML research tasks and benchmark problems.
• Develop expert-level reference solutions and evaluation methodologies.
• Create grading rubrics for model reasoning, implementation quality, and scientific correctness.
• Evaluate AI-generated solutions for technical accuracy and research validity.
• Author problem sets covering advanced ML concepts and research workflows.
• Review model outputs and identify weaknesses in reasoning, implementation, experimentation, and interpretation; document solutions and benchmarks.
• Contribute domain expertise to improve frontier AI evaluation systems.

Skills

First-author publication

Hands-on ML research

ML programming

Experimentation

Written communication

Research problem design

Education

Master's or PhD in ML/CS/Statistics/Mathematics

Job description

AfterQuery is seeking experienced Machine Learning Research Experts with a strong research track record to design benchmark tasks, evaluate model capabilities, and contribute expert-level ML reasoning to next-generation AI systems. The role emphasizes designing rigorous evaluation tasks and may focus on areas such as Language Models, Deep Learning, RL, CV, Generative AI, and more.

Fully remote, rolling applications, and asynchronous work are offered.