Principal AI Safety Engineer - Technical Mitigations Equity

Lilasciences; Greater London; Presencial; GBP 168 000 - 252 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

Equity options

Bonus potential

Resumo da oferta

Lila Sciences is seeking a Technical Mitigations Lead to build safety systems for deploying frontier-class AI within scientific workflows. You will design safeguards beyond current state-of-the-art and start the initial mitigations build-out while growing a small team.

This is a high-impact role spanning safety and core AI teams; you will shape research directions, communicate complex concepts to non-experts, and influence external safety communications.

Qualificações

• Track record of building safety systems, classifiers, or post-training work for frontier-class problems.
• Experience building scalable, production ML systems.
• Ability to set research directions for post-training, classifier buildouts, and related systems.
• Ability to communicate complex technical concepts to non-experts.
• Experience leading teams toward engineering goals.

Responsabilidades

• Set the build and research strategy for Lila’s safety systems across data analysis and generation pipelines, safety post-training, and monitoring.
• Lead a small team to execute the build and research agenda.
• Lead safety systems research beyond the state of the art for both in silico and lab-based workflows.
• Collaborate with safety, core AI, lab automation, and product teams.
• Contribute to external communications on Lila’s safety efforts.

Conhecimentos

Safety systems

ML systems

Post-training

Production systems

Research directions

Communication skills

Descrição da oferta de emprego

Lila Sciences is seeking a Technical Mitigations Lead to build safety systems for deploying frontier-class AI within scientific workflows. You will design safeguards beyond current state-of-the-art and start the initial mitigations build-out while growing a small team.

This is a high-impact role spanning safety and core AI teams; you will shape research directions, communicate complex concepts to non-experts, and influence external safety communications.