Research Scientist, Open Source Technical Safeguards

Core responsibilities:

• Develop technical safeguards against tampering with open weight models to mitigate AI-generated CSAM and NCII by targeting the real-world supply chain driving harm
• Synthesize threat intelligence on how AI-generated CSAM and NCII are developed and create scalable screening methodologies that platforms can realistically run
• Design and pilot scalable, automated screening methodologies platforms can run pre-publication on uploads
• Co-develop best-practice protocols with NGOs for hosting, app store, and OS enforcement

Your work will raise safety standards across hosting and distribution layers, reduce the availability of CSAM/NCII-generating artifacts on major platforms, inform industry protocols and possibly standards, and provide actionable evidence for government decisions.

Required skills and qualifications:

• At least 3+ years of relevant experience in applied ML, trust & safety tooling, content moderation, security engineering, or adjacent technical fields
• Deep familiarity with open-weight image/video models (diffusion, LoRA), model hosting ecosystems, and the limitations of pre-deployment safeguards
• Strong Python and ML stack (PyTorch/JAX), data engineering, and systems skills; experience building pipelines and tooling that run at platform scale
• Knowledge of fingerprinting and detection approaches and their privacy and robustness trade-offs
• Commit to work from our London office in Whitehall for parts of the week, with flexibility for remote work

Compensation and benefits:

• Annual salary between £65,000 and £145,000 (base plus technical allowance)
• 27% government-funded pension contribution on top of salary
• At least 25 days' annual leave, 8 public holidays, and extra team-wide breaks
• Generous paid parental leave (36 weeks of UK statutory leave shared between parents + 3 extra paid weeks)
• Modern central London office or option to work in similar government offices in Birmingham, Cardiff, Darlington, Edinburgh, Salford, or Bristol
• Hybrid working with opportunities for occasional remote work abroad
• 5 development days per year, annual L&D budget, and travel support for conferences
• Work from home equipment and dental insurance