Staff / Principal Research Engineer, AI Safety, Technical Mitigations

Responsibilities

Our talent team is representing a confidential AI research organization seeking a Staff or Principal Research Engineer to lead the technical mitigations function within their safety program. In this role, you will:

• Define and execute the build and research strategy for safety systems across data pipelines, post-training workflows, refusal classifiers, automated red-teaming systems, and monitoring infrastructure
• Conduct hands-on experimentation and initial buildout of safeguards tailored to specialized scientific workflows, then scale by building and leading a small team
• Drive safety systems research to advance capabilities beyond current state-of-the-art, addressing novel challenges in both computational and laboratory-based scientific processes
• Collaborate closely with domain experts in biological, chemical, and materials sciences, evaluation teams, core AI researchers, lab automation engineers, and product stakeholders
• Contribute to high-quality research efforts for capability evaluation and restriction where scientific risks are present
• Support external communications regarding the organization's safety approach and technical safeguards

What We're Looking For

We seek candidates with a proven track record in AI safety engineering who can operate independently and strategically:

• Demonstrated experience building safety systems, classifiers, or conducting post-training for frontier-class problems in domains such as science, reasoning, or programming
• 4-6+ years of hands-on technical engineering experience with machine learning systems
• Strong background building scalable, production-grade systems beyond prototype stage
• Proven ability to set research directions for open problems in post-training, classifier development, and related safety infrastructure
• Excellent communication skills, with ability to convey complex technical concepts to non-expert stakeholders

Highly valued but not required:

• Experience developing or applying ML to biological or physical sciences
• Background building safeguards for scientific risks associated with frontier models or specialized scientific tools
• Team leadership experience with demonstrated ability to guide engineering teams toward ambitious goals

How We Work With You

Candidates apply directly through Get A Job.ai. Our recruiting team will conduct an initial screening to understand your background and fit for this specialized role. Strong candidates are then submitted to our client for their interview process. Please do not contact the client organization directly—all communication flows through our team to ensure a smooth, professional experience.

Pay

This position is based in London. Compensation details will be discussed during the screening process based on experience and location.

Equal Employment Opportunity

Get A Job.ai is committed to equal employment opportunity regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity, or veteran status.