Staff / Principal Research Engineer, AI Safety Mitigations

Location: Cambridge, MA, USA; London, UK; or San Francisco, CA, USA

Expected base salary range: $224,000–$336,000 USD annually for U.S.-based positions. International salaries are set to local market.

Company

hirify.global is building scientific superintelligence by combining advanced AI models with proprietary AI Science Factory instruments to accelerate discovery across medicine, materials, and energy.

What you will do

• Translate scientific risk assessments, dual-use policy boundaries, and evaluation findings into mitigation designs and testable requirements.
• Develop safeguards across model training, classifiers, monitoring, access controls, and runtime interventions.
• Build experiments to measure risk reduction, robustness, legitimate scientific use, and practical performance.
• Use adversarial findings and observed failures to improve safeguards in collaboration with automated-safety and scientific evaluation researchers.
• Integrate mitigations with model-training, post-training, inference, and platform teams across development, release evaluation, and large-scale serving systems.
• Investigate regressions, distribution shifts, and emerging misuse patterns using reproducible testing and instrumentation.

Requirements

• Hands-on experience developing and validating safety interventions for frontier models in training, post-training, or large-scale inference systems.
• Depth in at least one area such as safety post-training, model-level classifiers, inference safeguards, or abuse monitoring and enforcement.
• Experience working with model-development or safeguards teams and using training pipelines, model internals, inference infrastructure, or systematic evaluation access.
• Strong research-engineering skills, including the ability to turn ambiguous problems into maintainable implementations.
• Sound experimental judgment and the ability to assess robustness, interpret imperfect metrics, and balance competing objectives.
• Ability to collaborate across research and engineering teams, explain technical trade-offs, and own complex individual contributions.

Nice to have

• 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 evidence and policy requirements to training data, evaluation criteria, or operational controls.

Culture & Benefits

• High-agency, cross-functional AI safety work with science, model-training, laboratory-integration, evaluation, and engineering teams.
• Competitive base compensation, bonus potential, and generous early-stage equity.
• U.S. full-time employees receive medical, dental, and vision coverage, life and disability insurance, flexible time off, paid parental leave, educational assistance, commuter benefits, and subsidized lunch.
• Full-time employees outside the U.S. receive benefits tailored to their region.
• Core values include truth, trust, curiosity, grit, and velocity.