Research Scientist, Gemini Agent Safety, DeepMind

Google LLC; Mountain View (CA); On-site; USD 174,000 - 252,000; Full time

Benefits offered by this job

Equity

Bonus target

Benefits

Job summary

Google DeepMind is seeking a Research Scientist for Gemini Agent Safety in Mountain View. You will develop algorithmic solutions to advance user-facing architectures and ensure outputs are aligned and production-ready, coordinating with Gemini post-training and core Product Area partners.

You will drive deep thinking and rigorous research, owning end-to-end safety implementations and mitigation frameworks while guiding cross-functional alignment across launch surfaces.

Qualifications

• PhD in Computer Science or a related field, or equivalent practical experience.
• 1 year of experience with Generative AI, LLMs, NLP, or Agent-based systems.

Responsibilities

• Design and implement algorithms to identify safety gaps in model behavior across Gemini and GenAI.
• Develop modeling and alignment techniques to address real-world safety challenges under tight launch timelines.
• Advance model optimization using SFT and RL at scale and coordinate with cross-functional teams.
• Collaborate with post-training, evaluation, and product teams to align safety decisions.

Skills

Generative AI

Large Language Models

NLP

Agent-based systems

Education

PhD in Computer Science or related field

Job description

Research Scientist, Gemini Agent Safety, DeepMind

Share Research Scientist, Gemini Agent Safety, DeepMind

corporate_fare DeepMind place Mountain View, CA, USA

• PhD in Computer Science, a related field, or equivalent practical experience.
• 1 year experience with Generative AI, Large Language Models, natural language processing, or Agent-based systems.

Preferred qualifications:

• Experience in AI safety and model alignment.
• Expertise in reward modeling, Reinforcement Learning (RL) for LLMs, instruction tuning, and long-range RL.
• Ability to drive research concepts to product realization with a strong track record of engineering abilities and experimental work.
• Track record of publications at AI/ML venues (e.g., NeurIPS, ICLR, ICML, EMNLP, AAAI, UAI).

About the job

The Gemini Safety team is accountable for the standards of GDM’s flagship releases. In this role, you will develop algorithmic solutions to advance user-facing architectures. The workstyle is changing, supported by a strong internal culture of mutual dedication and cooperation.

You will bring LLM post-training expertise to ensure outputs are aligned and production-ready. This scope encompasses deep thinking and deep research capabilities, coordinating directly with the Gemini post-training organization and core Product Area counterparts.

You will be a builder and shipper who takes end-to-end ownership. You will formulate mitigation frameworks and evaluations while guiding the cross-functional alignment required to deploy across launch surfaces.

Artificial intelligence will be one of humanity’s most transformative inventions. At Google DeepMind, we are a pioneering AI lab with exceptional interdisciplinary teams focused on advancing AI development to solve complex global challenges and accelerate high-quality product innovation for billions of users. We use our technologies for widespread public benefit and scientific discovery, ensuring safety and ethics are always our highest priority.

We are pushing the boundaries across multiple domains. Our global teams offer diverse learning opportunities and varied career pathways for those driven to achieve exceptional results through collective effort.Individual pay is determined by factors including job-related skills, experience, and relevant education or training.

US: $174000 - $252000 (USD) + 15% bonus target + equity + benefits

• Design, implement, and maintain high-quality protocols to identify safety gaps in model behavior across all Gemini and GenAI models, and feed these insights back into the post-training process to continuously improve both in-model and out-of-model protection.
• Explore, adapt, and apply innovative modeling and alignment techniques to solve real-world safety and alignment challenges under tight launch timelines.
• Drive innovation in model optimization, advancing the application of Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) techniques at massive scale.
• Partner closely with post-training, evaluation, and product teams to align incentives, close safety gaps, and influence safety decisions without direct authority.

Google is proud to be an equal opportunity and affirmative action employer. We are committed to building a workforce that is representative of the users we serve, creating a culture of belonging, and providing an equal employment opportunity regardless of race, creed, color, religion, gender, sexual orientation, gender identity/expression, national origin, disability, age, genetic information, veteran status, marital status, pregnancy or related condition (including breastfeeding), expecting or parents-to-be, criminal histories consistent with legal requirements, or any other basis protected by law. See also Google's EEO Policy , Know your rights: workplace discrimination is illegal , Belonging at Google , and How we hire .

Google is a global company and, in order to facilitate efficient collaboration and communication globally, English proficiency is a requirement for all roles unless stated otherwise in the job posting.

To all recruitment agencies: Google does not accept agency resumes. Please do not forward resumes to our jobs alias, Google employees, or any other organization location. Google is not responsible for any fees related to unsolicited resumes.

Equity is granted exclusively and discretionarily by Alphabet Inc. on the basis of an agreement concluded between you and Alphabet Inc. Alphabet Inc. is your sole contractual partner with respect to equity grants. GSU grants are not guaranteed, are discretionary, are subject to approval by the Alphabet Inc. board of directors or its delegate, the terms of the relevant Alphabet Inc. stock plan, and your grant agreement. They have no impact on statutory payments. Current or past grants do not confer an acquired right.