Research Scientist, Open-Source AI Safeguards

AI Security Institute; Greater London; Hybrid; GBP 65,000 - 145,000; Full time

Job summary

A leading AI research organization in London is seeking a Research Scientist with expertise in developing safeguards for open-source models. The successful candidate will focus on mitigating risks related to AI-generated harmful content, engaging with various stakeholders across government and industry. Ideal candidates will possess strong technical skills in machine learning, particularly with open-weight models. This position offers competitive compensation, unique opportunities for influence in AI governance, and the flexibility of hybrid working arrangements.

Benefits

Annual L&D budget

Generous paid parental leave

27% government-funded pension contribution

Qualifications

• 3+ years of relevant experience in applied ML, trust & safety tooling, content moderation.
• Familiarity with open‑weight image/video models and model hosting ecosystems.
• Strong methodological rigor and creativity.

Responsibilities

• Develop technical safeguards against tampering with open‑weight models.
• Synthesize threat intelligence on AI‑generated content.
• Publish best‑practice protocols with NGOs.

Skills

Applied ML

Content moderation

Security engineering

Python

Data engineering

Education

Relevant technical degree

Tools

PyTorch

JAX

Hugging Face

Job description

A leading AI research organization in London is seeking a Research Scientist with expertise in developing safeguards for open-source models. The successful candidate will focus on mitigating risks related to AI-generated harmful content, engaging with various stakeholders across government and industry. Ideal candidates will possess strong technical skills in machine learning, particularly with open-weight models. This position offers competitive compensation, unique opportunities for influence in AI governance, and the flexibility of hybrid working arrangements.