Staff / Principal Research Engineer, AI Safety Mitigations
Hybrid (Cambridge, MA; London, UK; San Francisco, CA)$224k - $336kFull-timePosted 4d ago
About the role
Role focused on building and implementing a bespoke safety strategy for Lila Sciences, mitigating risks from advanced AI systems in scientific contexts. Works with domain scientists, risk researchers, evaluators and engineering teams to translate risk findings into concrete safeguards and integrate them into model development, release evaluation and deployment.
Responsibilities
- 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.
Qualifications
- Hands-on experience developing and validating safety interventions for frontier models within training, post-training or large-scale inference systems, with contributions to model development or release cycles.
- 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.
Skills
Required:Safety interventions for frontier modelsModel development or safeguards collaboration
Benefits
- Full-time U.S. employees: comprehensive benefits including medical, dental, vision; employer-paid life and disability; flexible time off with generous holidays; paid parental leave; educational assistance; commuter benefits (bike share); subsidized lunch.
Last updated Oct 21, 2026. Interested? Apply on the company site.
About Lila Sciences
Pioneering Scientific Superintelligence
Pioneering Scientific Superintelligence to solve humankind’s greatest challenges.
Scientific SuperintelligenceAIAutonomous LabsLife SciencesChemical SciencesMaterials Sciences
More open roles at Lila Sciences
- Staff IT Systems Engineer, Endpoints4d agoCambridge, MA · Business Operations
- Principal Network Engineer4d agoCambridge, MA · Business Operations
- Contractor, P2P Specialist4d agoCambridge, MA · Corporate Development
- Specialist / Senior Procurement Specialist4d agoCambridge, MA · Corporate Development
- Staff / Principal Security Engineer, AI Safety and Security4d agoHybrid (Cambridge / London / San Francisco) · AI