Biologist | Remote

Crossing Hurdles; United States; Remote; GBP 60,000 - 100,000; Full time

Job summary

Crossing Hurdles in the United Kingdom is seeking an expert to design realistic life-sciences AI tasks, develop evaluation environments, and produce reference solutions to benchmark advanced models.

You will assess model outputs, identify faulty assumptions and data leakage, and ensure reproducible research across projects with rigorous evaluation criteria.

Qualifications

• Prior paid experience training, evaluating, benchmarking, or improving AI systems on scientific or technical tasks.
• Strong practical proficiency with Python.
• Deep expertise in at least one relevant life-science specialization.
• Hands-on experience using computational methods for modeling, simulation, bioinformatics, biomedical analysis, statistics, or reproducible research.

Responsibilities

• Create realistic computational life-science tasks that challenge advanced AI models.
• Develop task instructions, reproducible environments, reference solutions, and evaluation criteria.
• Evaluate model-generated code, analyses, models, experiments, and technical deliverables.
• Identify invalid biological assumptions, methodological errors, data leakage, statistical issues, or reproducibility failures.

Skills

Python

AI evaluation

Life sciences

Job description

• Create realistic computational life-science tasks that challenge advanced AI models.
• Develop task instructions, reproducible environments, reference solutions, and evaluation criteria.
• Evaluate model-generated code, analyses, models, experiments, and technical deliverables.
• Identify invalid biological assumptions, methodological errors, data leakage, statistical issues, or reproducibility failures.

Requirements

• Prior paid experience training, evaluating, benchmarking, or improving AI systems on scientific or technical tasks.
• Strong practical proficiency with Python.
• Deep expertise in at least one relevant life-science specialization.
• Hands-on experience using computational methods for modeling, simulation, bioinformatics, biomedical analysis, statistics, or reproducible research.