Staff Research Scientist, AI Alignment

About the job

As an organization, Google maintains a portfolio of research projects driven by fundamental research, new product innovation, product contribution and infrastructure goals, while providing individuals and teams the freedom to emphasize specific types of work. As a Research Scientist, you'll setup large-scale tests and deploy promising ideas quickly and broadly, managing deadlines and deliverables while applying the latest theories to develop new and improved products, processes, or technologies. From creating experiments and prototyping implementations to designing new architectures, our research scientists work on real-world problems that span the breadth of computer science, such as machine (and deep) learning, data mining, natural language processing, hardware and software performance analysis, improving compilers for mobile platforms, as well as core search and much more.

As a Research Scientist, you'll also actively contribute to the wider research community by sharing and publishing your findings, with ideas inspired by internal projects as well as from collaborations with research programs at partner universities and technical institutes all over the world.

In this role, you will serve as a key researcher for regional AI safety research, establishing a technical presence dedicated to AI alignment. You will bridge foundational academic breakthroughs with core engineering execution to ensure next-generation AI models are robust, trustworthy, and safe. You will act as a key liaison, building and coordinating highly impactful research partnerships with academic institutions, government stakeholders, and regional engineering hubs across the Asia-Pacific (APAC) region. You will also actively contribute to the wider research community by sharing and publishing findings.

Responsibilities

• Serve as the lead researcher for regional AI safety research, defining and driving a foundational research agenda in AI alignment and developing advanced computational intelligence technology to adapt to new trends and threats.and socio-technical systems.
• Lead local interactions and liaise directly with APAC academic institutions, government bodies, and key external stakeholders to establish and coordinate joint research partnerships.
• Oversee the strategic integration of localized safety breakthroughs, evaluation protocols, and alignment methodologies into core engineering frameworks and frontier AI models.
• Collaborate closely with regional engineering teams, global research pillars, and cross-functional partners to navigate fast-moving technology policy and regulatory landscapes.
• Participate in the regional research community, publish foundational research in scientific venues, represent Google in regional research forums, and mentor students or visiting researchers.

Qualifications

Minimum qualifications:

• PhD degree in Computer Science, a related field, or equivalent practical experience.
• 4 years of experience with research agendas across multiple teams or projects.
• Experience in machine learning, adversarial machine learning or evaluating frontier AI systems, which includes but not limited to supervised learning, unsupervised learning and reinforcement learning, ML interpretability, adversarial robustness, ML safety, generative models, agentic AI, multi-object optimization.
• One of more scientific publication submission(s) for conferences, journals, or public repositories (such as CVPR, ICCV, NeurIPS, ICML, ICLR, etc.).

Preferred qualifications:

• Experience establishing research partnerships or liaising with external stakeholders, academic institutions, or government bodies.
• Demonstrated experience understanding technology policy, regulatory compliance, and regional cultural nuances within the Asia-Pacific (APAC) landscape.
• Track record of successfully coordinating joint academic research initiatives and integrating advanced research breakthroughs into scalable engineering frameworks.
• First-authored publications in top machine learning, safety/security tracks in machine learning or AI conferences, or HCI conferences.