Google DeepMind
Research Scientist Tech Lead, Contextual Security
Google DeepMind, New York, New York, us, 10261
Research Scientist Tech Lead, Contextual Security
Snapshot
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. 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.
About Us Leveraging our best-in-industry auto-red teaming capabilities, our mission is to unblock the strongest and most helpful agentic GenAI capabilities in the real world. Doing so will make Gemini and other GenAI models as capable as highly experienced privacy and security engineers in handling sensitive user data and permissions. We have already delivered a substantial improvement in prompt injection resilience in Gemini 3.0, and are continuing to partner closely with other GDM teams to bring security and privacy into all aspects of Gemini post-training.
The Role As a Technical Lead and Manager for Contextual Security in the GDM Security & Privacy Research team, you will be responsible for:
Lead the existing team to address key challenges in contextual security with connections to prompt injection, from leading the fundamental research to providing out the solutions for key products.
Manage a team of researchers with extensive background in security and machine learning, as well as grow the team to keep up with the rapid evolving space of contextual security problems
Identifying unsolved, impactful privacy & security problems present in generative models through auto-red teaming, with priorities guided by securing critical products and product features
Building post-training data and tools hypothesised to improve model capabilities in the problem areas, testing the hypotheses through evaluations and auto-red teaming, and contributing successful solutions into Gemini and other models.
Amplifying the impact by generalizing solutions into reusable libraries and frameworks for protecting agents and models across Google, and by sharing knowledge through publications, open source, and education.
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:
PhD in Computer Science or related quantitative field OR 5+ years of relevant experience.
Demonstrated experience driving complex research projects in AI security, security, privacy or safety
Experience managing teams of ~5-10 individual contributors
In addition, the following would be an advantage:
Demonstrated experience driving complex projects to landing in production or adoption in open source
Demonstrated experience in adapting research outputs into impactful model improvements, in a rapidly shifting landscape and with a strong sense of ownership.
Research experience and publications in ML security, privacy, safety, or alignment.
Experience working on contextual security or prompt injection.
The US base salary range for this full-time position is between $248,000 USD - 349,000 USD + bonus + equity + benefits. Your recruiter can share more about the specific salary range for your targeted location during the hiring process.
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 opportunity 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.
Google DeepMind is subject to certain governmental recordkeeping and reporting requirements for the administration of civil rights laws and regulations. In order to comply with these laws and achieve our goal of a diverse and inclusive workforce, Google DeepMind invites employees to voluntarily self-identify their race or ethnicity. Submission of this information is voluntary and refusal to provide it will not subject you to any adverse treatment. The information obtained will be kept confidential and may only be used in accordance with the provisions of applicable laws, executive orders, and regulations, including those that require the information to be summarized and reported to the federal government for civil rights enforcement. When reported, data will not identify any specific individual. If you'd like more information about your EEO rights as an applicant under the law, please click here https://www.eeoc.gov/employers/eeo-law-poster.
#J-18808-Ljbffr
About Us Leveraging our best-in-industry auto-red teaming capabilities, our mission is to unblock the strongest and most helpful agentic GenAI capabilities in the real world. Doing so will make Gemini and other GenAI models as capable as highly experienced privacy and security engineers in handling sensitive user data and permissions. We have already delivered a substantial improvement in prompt injection resilience in Gemini 3.0, and are continuing to partner closely with other GDM teams to bring security and privacy into all aspects of Gemini post-training.
The Role As a Technical Lead and Manager for Contextual Security in the GDM Security & Privacy Research team, you will be responsible for:
Lead the existing team to address key challenges in contextual security with connections to prompt injection, from leading the fundamental research to providing out the solutions for key products.
Manage a team of researchers with extensive background in security and machine learning, as well as grow the team to keep up with the rapid evolving space of contextual security problems
Identifying unsolved, impactful privacy & security problems present in generative models through auto-red teaming, with priorities guided by securing critical products and product features
Building post-training data and tools hypothesised to improve model capabilities in the problem areas, testing the hypotheses through evaluations and auto-red teaming, and contributing successful solutions into Gemini and other models.
Amplifying the impact by generalizing solutions into reusable libraries and frameworks for protecting agents and models across Google, and by sharing knowledge through publications, open source, and education.
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:
PhD in Computer Science or related quantitative field OR 5+ years of relevant experience.
Demonstrated experience driving complex research projects in AI security, security, privacy or safety
Experience managing teams of ~5-10 individual contributors
In addition, the following would be an advantage:
Demonstrated experience driving complex projects to landing in production or adoption in open source
Demonstrated experience in adapting research outputs into impactful model improvements, in a rapidly shifting landscape and with a strong sense of ownership.
Research experience and publications in ML security, privacy, safety, or alignment.
Experience working on contextual security or prompt injection.
The US base salary range for this full-time position is between $248,000 USD - 349,000 USD + bonus + equity + benefits. Your recruiter can share more about the specific salary range for your targeted location during the hiring process.
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 opportunity 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.
Google DeepMind is subject to certain governmental recordkeeping and reporting requirements for the administration of civil rights laws and regulations. In order to comply with these laws and achieve our goal of a diverse and inclusive workforce, Google DeepMind invites employees to voluntarily self-identify their race or ethnicity. Submission of this information is voluntary and refusal to provide it will not subject you to any adverse treatment. The information obtained will be kept confidential and may only be used in accordance with the provisions of applicable laws, executive orders, and regulations, including those that require the information to be summarized and reported to the federal government for civil rights enforcement. When reported, data will not identify any specific individual. If you'd like more information about your EEO rights as an applicant under the law, please click here https://www.eeoc.gov/employers/eeo-law-poster.
#J-18808-Ljbffr