Agentic Safety and Ecosystem Architect, Trust and Safety

Agentic Safety and Ecosystem Architect, Trust and Safety

_corporate_fare_ Google _place_ Kirkland, WA, USA;
Austin, TX, USA; +2 more; +1 more

** Mid*
* Experience driving progress, solving problems, and mentoring more junior team members; deeper expertise and applied knowledge within relevant area.

_info_outline_

XIn accordance with Washington state law, we are highlighting our comprehensive benefits package, which is available to all eligible US based employees. Benefits for this role include:

+ Health, dental, vision, life, disability insurance

+ Retirement Benefits: 401(k) with company match

+ Paid Time Off: 20 days of vacation per year, accruing at a rate of 6.15 hours per pay period for the first five years of employment

+ Sick Time: 40 hours/year (increased to 69 hours/year for Seattle) including 5 discretionary sick days per instance

+ Maternity Leave (Short-Term Disability + Baby Bonding): 28-30 weeks

+ Baby Bonding Leave: 18 weeks

+ Holidays: 13 paid days per year

Note:

By applying to this position you will have an opportunity to share your preferred working location from the following:
** Kirkland, WA, USA;
Austin, TX, USA;
Atlanta, GA, USA** .

*
* Minimum qualifications:

*
* + Bachelor's degree or equivalent practical experience.

+ 7 years of experience in data analytics, Trust and Safety, policy, cybersecurity, or related fields.

+

Experience with ML/AI based programs in Trust and Safety.

*
* Preferred qualifications:

*
* + Master's degree or PhD in a relevant field.

+ Experience in agentic architecture and data permissions.

+ Experience in technical product design and AI systems.

+ Experience in program management.

+ Understanding of AI/ML system safety and integrity.

** About the job*
* Trust & Safety team members are tasked with identifying and taking on the biggest problems that challenge the safety and integrity of our products. They use technical know-how, excellent problem-solving skills, user insights, and proactive communication to protect users and our partners from abuse across Google products like Search, Maps, Gmail, and Google Ads. On this team, you're a big-picture thinker and strategic team-player with a passion for doing what's right.

You work globally and cross-functionally with Google engineers and product managers to identify and fight abuse and fraud cases at Google speed - with urgency. And you take pride in knowing that every day you are working hard to promote trust in Google and ensuring the highest levels of user safety.

As an Agentic Safety and Ecosystem Architect, you will design for the safety and integrity of autonomous AI agents across the Android platform. Your focus is to bridge the gap between technical agent capabilities and the real-world safety of billions of users. You will be responsible for identifying and mitigating the harms that arise when AI agents interact with the OS and third-party apps-ranging from system-level instability to the creation of harmful synthetic media.

By developing detection nets and enforcement frameworks, you will ensure that agentic features do not become vectors for abuse.

At Google we work hard to earn our users' trust every day. Trust & Safety is Google's team of abuse fighting and user trust experts working daily to make the internet a safer place. We partner with teams across Google to deliver bold solutions in abuse areas such as malware, spam and account hijacking. A team of Analysts, Policy Specialists, Engineers, and Program Managers, we work to reduce risk and fight abuse across all of Google's products, protecting our users, advertisers, and publishers across the globe in over 40 languages.

Individual pay is determined by factors including job-related skills, experience, and relevant education or training.

US: $141000 - $206000 (USD) + 15% bonus target + equity + benefits

Learn more about benefits at Google () .

** Responsibilities*
* + Develop the rules of engagement for autonomous agents on Android, ensuring that multi-step plans are audited for safety before execution.

+ Implement strict "least-privilege" models so agents cannot escalate system permissions or access sensitive user data without explicit, context-aware consent.

+ Partner with the Product team to build runtime monitoring that identifies "agentic drift," recursive loops, or adversarial attempts to hijack agent reasoning.

+ Create self-testing kits for the Android developer community to ensure that third-party agents are built with brakes and kill-switches.

Information collected and processed as part of your Google Careers profile, and any job applications you choose to submit is subject to Google'sApplicant and Candidate Privacy Policy (./privacy-policy) .

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,…