SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 224,000 - 336,000 / annual
Lila Sciences is building Scientific Superintelligence to solve major scientific challenges by combining advanced AI models with proprietary instruments into an operating system for autonomous science. You will join a talent-dense, high-agency AI safety team as a Staff/Principal Research Engineer focused on developing and implementing safeguards that reduce societal risks from increasingly capable closed-loop scientific AI systems.
Your core mission is to translate scientific risk assessments, dual-use policy boundaries, and evaluation findings into concrete mitigation designs and testable requirements. You will develop and implement safeguards suited to specific problems, potentially spanning model training, classifiers, monitoring, access controls, and runtime interventions. Your work spans both research and implementation: developing approaches, testing their limits, and helping integrate reliable safeguards into systems where they are needed.
Key responsibilities include:
- Translating risk assessments and policy requirements into concrete mitigation designs and testable requirements
- Developing and implementing safeguards across model training, post-training, inference, and platform layers
- Building experiments that measure risk reduction, robustness, and effects on legitimate scientific use
- Using adversarial findings and observed failures to improve safeguards in collaboration with safety and scientific evaluation researchers
- Working directly with model-training, post-training, inference, and platform teams to integrate mitigations into model development, release evaluation, and large-scale serving systems
- Investigating regressions, distribution shifts, and emerging misuse patterns to guide further development
You will collaborate across domain scientists, risk researchers, evaluators, and engineering teams to turn findings into effective interventions. This is a high-priority individual contributor role with significant technical scope and influence over safety strategy implementation.
REQUIREMENTS:
- 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: 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 (training pipelines, model internals, inference infrastructure, or systematic evaluation access) to investigate failures and implement improvements
- Strong research-engineering skills and ability to move from ambiguous problems to working, maintainable implementations
- Sound experimental judgment, including ability to assess robustness, interpret imperfect metrics, and reason about competing objectives
- Ability to collaborate across research and engineering teams, explain technical trade-offs, and take ownership of complex individual contributions
BONUS QUALIFICATIONS:
- Experience with scientific models, scientific software, or laboratory-connected systems
- Safety work involving tool-using agents, multi-step workflows, or high-consequence misuse
- Experience connecting expert-generated evidence and policy requirements to training data, evaluation criteria, or operational controls
