Senior Specialist / Manager, AI Safety Data and Evaluation Program

Highlights

• Build bespoke AI safety strategy for scientific superintelligence at Lila.
• Run red-teaming and evaluation campaigns generating safety evidence.
• Turn scientific risk questions into expert-data programs for leadership.

Ideal candidate

Operations-minded AI safety practitioner who thrives running expert programs and red-teaming with scientists. High-agency, detail-obsessed collaborator passionate about turning misuse risks into evidence for safe scientific discovery.

Requirements

• Experience delivering expert-data, research-operations, evaluation or similarly demanding programs involving specialist contributors.
• A substantial working understanding of AI safety, including how threat models, capability evaluations, red teaming and safeguards inform one another.
• Evidence of applying this safety understanding in research, evaluation or expert-data work, including how it shaped scoping, execution or review.
• Strong operational judgment and the ability to manage dependencies, changing requirements and several parallel workstreams.
• A track record of setting measurable quality standards, detecting recurring problems and improving data processes.
• Clear communication, careful documentation and ability to build relationships with researchers, experts and vendors.