Staff / Principal Research Engineer, AI Safety Mitigations

Sourced from threadangellabs.com

Lila Sciences is hiring a Staff/Principal Research Engineer to build and validate safety mitigations for frontier scientific AI models. The role spans research and implementation, translating risk assessments and policy boundaries into concrete safeguards across training, post-training, inference, and serving systems. You will work with domain scientists, risk researchers, and engineering teams to reduce societal risks while preserving scientific discovery capabilities.

• Translate scientific risk assessments, dual-use policy boundaries, and evaluation findings into concrete mitigation designs and testable requirements
• Develop and implement safeguards spanning model training, classifiers, monitoring, access controls, 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 automated-safety and evaluation researchers
• Integrate mitigations into model development, release evaluation, and large-scale serving systems with instrumentation and reproducible testing
• Investigate regressions, distribution shifts, and emerging misuse patterns to guide further development