AI Safety Programs Lead — Expert Data & Evaluation

Lilasciences; Greater London; A distancia; GBP 66.000 - 108.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Equity

Bonus potential

Descripción de la vacante

Lila Sciences is building a high‑agency AI safety team to identify and mitigate risks across core science and deployment workflows. The role focuses on program execution, data quality, and coordinating expert contributors to inform senior leadership decisions on safety strategies.

You will run red‑teaming, evaluation campaigns and gather feedback from AI safety partners, translating briefs into executable plans and maintaining rigorous data provenance and documentation.

Formación

• 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 the scoping, execution or review of a program.
• 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 the processes that produce data.
• Clear communication, careful documentation and the ability to build effective relationships with researchers, experts and vendors.
• Sufficient technical and scientific fluency to understand research briefs, clarify ambiguity and work productively with subject-matter experts.

Responsabilidades

• Organize contributors, run red‑teaming and evaluation campaigns, and ensure outputs meet defined standards.
• Translate briefs into executable plans with milestones, instructions and quality rubrics.
• Source and coordinate external experts and provide access to relevant expertise within the organization.
• Manage onboarding, task assignment, training and support so specialists contribute consistently.
• Oversee expert-data collection, annotation, and evaluation programs and track progress.
• Maintain clear records, versioned guidance and usable datasets; improve workflows based on feedback.

Conocimientos

Expert-data programs

AI safety

Threat modeling

Operational judgment

Communication

Herramientas

Annotation platforms

Data provenance tracking

Scripting

Descripción del empleo

Lila Sciences is building a high‑agency AI safety team to identify and mitigate risks across core science and deployment workflows. The role focuses on program execution, data quality, and coordinating expert contributors to inform senior leadership decisions on safety strategies.

You will run red‑teaming, evaluation campaigns and gather feedback from AI safety partners, translating briefs into executable plans and maintaining rigorous data provenance and documentation.