Computational Life Sciences Task Designer

Design multi-step computational life sciences tasks that test whether AI agents can inspect data, run code, solve problems, and explain results. This remote contractor role pays $280 per approved task.

$280/label

Compensation

Contract, part-time

Engagement

Remote

Location

Sep 22, 2026

Posted

You will turn real computational life sciences workflows into self-contained tasks for evaluating AI agents. Each task should test practical scientific work, from inspecting data and choosing methods to running code, troubleshooting, analyzing results, and presenting conclusions.

• Create input files, datasets, instructions, constraints, and expected deliverables.
• Build tasks with executable code, reproducible solutions, and objectively verifiable results.
• Check scientific assumptions, calculations, code, intermediate outputs, and final answers.
• Create automated or partly automated grading criteria that measure scientific reasoning and execution.
• Make sure tasks run reproducibly in controlled environments without network access.
• Use reviewer feedback while maintaining task quality and throughput.

This is a remote contractor assignment for a five-week contract. The work requires regular availability and a four-hour overlap with Pacific Time.

• Pay: $280 per approved task.
• Time: 20 or more hours per week.
• Education:
  
  Ph.D., postdoctoral experience, or equivalent research experience in the life sciences.
• Programming:
  Strong scientific programming experience, especially in Python.
• Analysis:
  Experience with multi-step computational scientific analyses and independently checking scientific reasoning and computational outputs.
• Task design:
  Ability to create bounded, objectively gradable tasks from authentic research workflows.
• Helpful background:
  Bioinformatics, computational genomics, systems biology, computational neuroscience, biostatistics, computational drug discovery, computational biochemistry, structural biology, protein engineering, or computational microbiology.
• Helpful tools:
  Scientific libraries, command-line tools, and reproducible research pipelines.

AI training work uses examples prepared and reviewed by people to improve how artificial intelligence systems perform. In this role, your scientific expertise helps create reliable tasks that test whether AI agents can carry out real computational research workflows.

• Experience:
  
  Entry level