GenAI Safety & Alignment Research Scientist

DeepMind Technologies Limited; New York (NY); In loco; USD 207.000 - 300.000; Tempo pieno

Descrizione del lavoro

DeepMind Technologies Limited is seeking a Research Scientist/Engineer to advance safety and reliability for foundational AI systems. You will lead investigations from concept to live release, balancing experimentation with rapid incident mitigation, and contribute to ethically aligned AI across consumer interfaces, APIs, and core platforms.

The role emphasizes collaborative, fast-paced work with a mission to push the boundaries of safe, useful AI.

Competenze

• PhD in Computer Science or related field or equivalent practical experience.
• 2 years of experience in Large Language Model safety or security.

Mansioni

• Drive safety and security mitigations for frontier GenAI models at scale with product teams.
• Develop red and blue teaming methods for GenAI safety and adversarial evaluation.
• Explore data, reasoning and algorithmic approaches to ensure Gemini models are safe and helpful.
• Improve adversarial robustness focusing on high-stakes abuse risks in agentic settings.
• Design and execute experimental plans to address known gaps or build new capabilities.

Conoscenze

LLM safety

Security expertise

Experimentation

Formazione

PhD in Computer Science or related field

Descrizione del lavoro

DeepMind Technologies Limited is seeking a Research Scientist/Engineer to advance safety and reliability for foundational AI systems. You will lead investigations from concept to live release, balancing experimentation with rapid incident mitigation, and contribute to ethically aligned AI across consumer interfaces, APIs, and core platforms.

The role emphasizes collaborative, fast-paced work with a mission to push the boundaries of safe, useful AI.