
Staff / Principal Research Engineer, AI Safety Mitigations
AI
Lila Sciences is seeking a Staff/Principal Research Engineer for AI Safety Mitigations in London. The role involves developing and testing safeguards for frontier scientific AI models, working across research and engineering teams. Requires hands-on experience with safety interventions in model training, post-training, or large-scale inference systems.
What you'll do
- Translate scientific risk assessments, dual-use policy boundaries and evaluation findings into concrete mitigation designs and testable requirements.
- Develop and implement safeguards suited to the problem, potentially spanning model training, classifiers, monitoring, access controls and runtime interventions.
- Build experiments that measure risk reduction, robustness and effects on legitimate scientific use, alongside practical performance constraints.
What you need
Must-have
AI SafetyModel TrainingPost-trainingInference SystemsClassifiersMonitoringAccess ControlsRuntime Interventions
Nice-to-have
Scientific ModelsScientific SoftwareLaboratory-connected SystemsTool-using AgentsMulti-step WorkflowsHigh-consequence MisusePolicy RequirementsOperational Controls
Soft skills
CollaborationCommunicationOwnershipProblem-solvingAdaptabilityCritical Thinking
AI SafetyResearch EngineerStaffPrincipalFrontier ModelsScientific AIMitigationsLondonHybridFull-time