Research Scientist, Multimodal Alignment, Safety, and Fairness

Research Scientist, Multimodal Alignment, Safety, and Fairness

Kirkland, Washington, US; Mountain View, California, US; New York City, New York, US

Snapshot

We are seeking strong Research Scientists with expertise in AI research and experience in interdisciplinary sociotechnical modeling to join a multimodal safety research effort within Google DeepMind's Frontier AI unit. This role requires a passion for understanding and modeling the interactions between AI and society, a strong awareness of the AI alignment and safety landscape, and a penchant for developing novel ideas, methods, interfaces, and tools.

This is a unique opportunity to contribute to impactful research and advance Google DeepMind's mission towards Artificial General Intelligence (AGI).

About Us

Artificial Intelligence could be one of humanity's most useful inventions. At Google DeepMind, we're a team of scientists, engineers, machine learning experts and more, working together to advance the state of the art in artificial intelligence and ultimately achieve Artificial General Intelligence. We use our technologies for widespread public benefit and scientific discovery, and collaborate with others on critical challenges, ensuring safety and ethics are the highest priority.

We're a dedicated scientific community, committed to "solving intelligence" and ensuring our technology is used for widespread public benefit.

Our team is a part of Google DeepMind's Frontier AI unit. We have a mission to advance the frontiers of safety and inclusion in multimodal AI, build new capabilities into Google's flagship models and products, and break new ground on AI alignment. We approach alignment research with an ecosystem view, partnering across the development and deployment cycle and grounding our work in real-world impact on global users and communities. We are a research team with a mandate to invest in longer term bets and explore innovative approaches that deliver breakthrough improvements to models (Gemini) and products. Our work is at the frontier of augmented oversight for multimodal AI, and our research advances have directly impacted multiple versions of Gemini and Nano Banana models.

The Role

We are seeking strong Research Scientists with expertise in AI research and experience in interdisciplinary sociotechnical modeling, to lead new breakthrough research directions.

You will join a team working to supercharge exploration, assessment, and steering of evolving AI behaviors, with a focus on subjective and creative tasks. You will tackle the underlying research questions to improve collaborative specification of alignment objectives and assessment of adherence to desired behaviors. You will research new methods to enable AI agents to monitor real-world social context and dynamically evaluate and evolve system behaviors over long time-horizons. You'll develop new paradigms for human+AI rating that considers systemic behaviors, adapts to human feedback, and proactively seeks context.

Research Scientists at Google DeepMind lead the development of novel tools and algorithms to solve Artificial General Intelligence. Joining from top academic or industrial labs, they collaborate across fields to tackle fundamental AI questions using expertise in deep learning, computer vision, and generative architectures. This role requires independent judgment to navigate complex, ambiguous problems and explore diverse technical avenues. Your work will drive breakthroughs within GDM, Google products, and the AI alignment community.

Key Responsibilities

• Research: Generate new ideas, keep up with the state of the art in the field, discuss research directions with other researchers.
• Execute: Design, rapidly implement, and rigorously evaluate cutting-edge ideas, methods, interfaces, and tools to explore new sociotechnical AI systems.
• Communicate: Report and present research findings and developments clearly and efficiently both internally and externally, verbally and in writing.
• Collaborate: Suggest and engage in inter- and intra- team collaborations to meet ambitious research goals, while also driving significant individual contributions.
• Drive technical projects: Take ownership of substantial technical projects, from ideation and design to implementation and evaluation, often involving cross-functional collaboration.

About You

In order to set you up for success as a Research Scientist at Google DeepMind, we look for the following skills and experience:

Requirements:

• PhD degree in Computer Science, Machine Learning, or a related technical field.
• Strong publication record in top machine learning conferences (e.g., NeurIPS, CVPR, ICML, ICLR, ICCV, ECCV).
• Demonstrated hands-on experience in developing multimodal AI models and systems,
• Strong programming skills in Python and experience with at least one major deep learning framework (e.g., JAX/Flax/Gemax)
• Experience conducting independent research and development, including experimental design, implementation, and analysis.

In addition, the following would be an advantage:

• Proven expertise in working with and tuning large-scale vision language models.
• Experience prototyping with VLMs with modern prompting strategies
• Experience finetuning and post-training LLMs using RL
• Experience with developing agentic AI solutions to complex problems
• Excited to collaborate across orgs and disciplines to leverage diverse perspectives and expertise and find creative solutions.
• Interest and a strong awareness of the AI alignment / safety / responsibility / fairness landscape
• Experience with Generative AI techniques and architectures.
• Familiarity with Reinforcement Learning or alignment methods.
• Experience with multimodal learning, integrating information from different data types (e.g., vision, audio, text).

The US base salary range for this full-time position is between 147,000 USD - 211,000 USD + bonus + equity + benefits. Your recruiter can share more about the specific salary range for your targeted location during the hiring process.

Note: In the event your application is successful and an offer of employment is made to you, any offer of employment will be conditional on the results of a background check, performed by a third party acting on our behalf. For more information on how we handle your data, please see our Applicant and Candidate Privacy Policy.

At Google DeepMind, we value diversity of experience, knowledge, backgrounds and perspectives and harness these qualities to create extraordinary impact. We are committed to equal employment opportunities regardless of sex, race, religion or belief, ethnic or national origin, disability, age, citizenship, marital, domestic or civil partnership status, sexual orientation, gender identity, pregnancy, or related condition (including breastfeeding) or any other basis as protected by applicable law. If you have a disability or additional need that requires accommodation, please do not hesitate to let us know.