Senior AI Safety Mitigations Engineer

Resume Skip; Greater London; On-site; GBP 168,000 - 252,000; Full time

Job summary

Lila Sciences is building Scientific Superintelligence™ to solve humankind's greatest challenges. We are hiring a high-impact engineer to develop and test safeguards that reduce societal risks from increasingly capable scientific AI, spanning models, agents, tools and lab workflows.

You will collaborate with domain scientists, risk researchers and engineering teams to turn risk findings into effective interventions, merging research and implementation across training, post-training and inference

Qualifications

• Hands-on experience developing and validating safety interventions for frontier models.
• Depth in at least one area, such as safety post-training, model-level classifiers, safeguards integrated into inference, or abuse monitoring.
• Experience working with model-development or safeguards teams with appropriate access to investigate failures.
• Strong research-engineering skills to move from an ambiguous problem to working implementations.
• Sound experimental judgment to assess robustness and metrics.
• Ability to collaborate across research and engineering teams.

Responsibilities

• Translate scientific risk assessments and evaluation findings into concrete mitigation designs and testable requirements.
• Develop and implement safeguards spanning model training, classifiers, monitoring, and runtime interventions.
• Build experiments measuring risk reduction, robustness, and effects on legitimate scientific use.
• Use adversarial findings and observed failures to improve safeguards with researchers.
• Collaborate with model-training, post-training, inference and platform teams to integrate mitigations into the development and deployment pipelines.
• Investigate regressions and distribution shifts to guide further development.

Skills

Safety engineering

Model evaluation

Inference systems

Cross-team collaboration

Experiment design

Tools

Training pipelines

Model internals

Inference infrastructure

Job description

Lila Sciences is building Scientific Superintelligence™ to solve humankind's greatest challenges. We are hiring a high-impact engineer to develop and test safeguards that reduce societal risks from increasingly capable scientific AI, spanning models, agents, tools and lab workflows.

You will collaborate with domain scientists, risk researchers and engineering teams to turn risk findings into effective interventions, merging research and implementation across training, post-training and inference