Principal AI Safety Engineer - Frontier Model Mitigations

Lila Sciences, Inc.; Greater London; Sur place; GBP 168 000 - 252 000; Plein temps

Résumé du poste

Lila Sciences is building Scientific Superintelligence safety into its research and deployment workflows, assembling a high-agency AI safety team that partners with science, model training, lab integration and evaluation functions to identify and mitigate risks in scientific AI systems.

We are seeking an engineer who has built safety interventions for frontier models and wants to apply that experience to scientific models, agents, tools, and laboratory-connected workflows.

Qualifications

• Hands-on experience developing and validating safety interventions for frontier models within training, post-training or large-scale inference systems.
• Depth in at least one relevant area, such as safety post-training, model-level classifiers, safeguards integrated into inference, or abuse monitoring and enforcement across a model-serving platform.
• Experience working directly with model-development or safeguards teams, using access appropriate to the intervention—such as training pipelines, model internals, inference infrastructure or systematic evaluation access—to investigate failures and implement improvements.
• Strong research-engineering skills and the ability to move from an ambiguous problem to working, maintainable implementations.
• Sound experimental judgment, including an ability to assess robustness, interpret imperfect metrics and reason about competing objectives.
• The ability to collaborate across research and engineering teams, explain technical trade-offs and take ownership of complex individual contributions.

Responsabilités

• 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.
• Use adversarial findings and observed failures to improve safeguards, working closely with automated-safety and scientific evaluation researchers.
• Work directly with model-training, post-training, inference and platform teams to integrate mitigations into model development, release evaluation and large-scale serving systems, with appropriate instrumentation and reproducible testing.
• Investigate regressions, distribution shifts and emerging misuse patterns, and use the evidence to guide further development.

Connaissances

Safety interventions

Research-engineering

Experimentation judgment

Cross-team collaboration

Description du poste

Lila Sciences is building Scientific Superintelligence safety into its research and deployment workflows, assembling a high-agency AI safety team that partners with science, model training, lab integration and evaluation functions to identify and mitigate risks in scientific AI systems.

We are seeking an engineer who has built safety interventions for frontier models and wants to apply that experience to scientific models, agents, tools, and laboratory-connected workflows.