Lead AI Safety & Biosecurity Scientist

Basecamp Research; Greater London; Hybrid; GBP 95,000 - 150,000; Full time

Benefits offered by this job

Impactful Mission

Collaborative Culture

High Growth

Comprehensive Benefits

Job summary

Basecamp Research is building frontier AI for therapeutic design, with EDEN models trained on proprietary genomic data and offices in London and Boston. You will advance AI safety and biosecurity, evaluating capabilities and developing safeguards while collaborating with biologists, engineers, and ML scientists.

You will lead projects from questions to experiments, publish findings, and help shape research priorities. A PhD or equivalent is expected, with a track record of impactful work.

Qualifications

• PhD or equivalent research record with publications in related areas.
• Strong track record in evaluating ML systems for safety and reliability.
• Experience collaborating with biology/experimental teams or cross-disciplinary projects.

Responsibilities

• Design evaluations and red-teaming studies for biological AI systems.
• Develop threat models and work with experimental teams to assess real-world risk.
• Investigate model behavior, representations, and generalisation to validate safety evaluations.
• Develop and test safeguards across training, model behavior, and access controls.

Skills

Machine learning

AI safety

Computational biology

Biosecurity

Model evaluation

Interpretability

Education

PhD in relevant field

Job description

Basecamp Research is building frontier AI for therapeutic design, with EDEN models trained on proprietary genomic data and offices in London and Boston. You will advance AI safety and biosecurity, evaluating capabilities and developing safeguards while collaborating with biologists, engineers, and ML scientists.

You will lead projects from questions to experiments, publish findings, and help shape research priorities. A PhD or equivalent is expected, with a track record of impactful work.