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. The Workspace AI Trust and Safety team enables the rapid growth of Workspace AI businesses by curbing associated safety and security risks. We support products throughout their life cycle by advancing safety protection mechanisms in the earliest stages of design. Our portfolio includes both pre and post-launch capabilities, ensuring AI products are powerful, safe, secure, and aligned with our AI Principles. As the Staff Analyst for Workspace AI Trust and Safety, you will move beyond individual execution to define the direction for how we measure, mitigate, and prevent AI risks at scale. You will serve as the technical anchor for a team of analysts, setting the standards for our anti-abuse detection systems and safety frameworks.
Responsibilities
Define the technical roadmap and long-term strategy for AI safety, prompt injection evaluations, and misuse prevention across Workspace AI Products.
Lead the design and implementation of scalable anti-abuse detection and action systems, including the "AI agent" frameworks used to automate enforcement.
Lead the investigation of novel and failure modes for GenAI products (e.g., sociotechnical harms, adversarial misuse) and establish benchmarking and evaluation protocols.
Act as a trusted advisor to executive stakeholders in Engineering and Product, translating safety and security risks into actionable business insights and influencing product design to prioritize safety.
Mentor analysts, review technical work, and elevate the team’s capabilities in data extraction, statistical analysis, and machine learning.
Qualifications
Minimum
Bachelor's degree or equivalent practical experience. 7 years of work experience in data analysis, security threat detection, or abuse investigation. Experience in one or more programming languages (e.g., Python, SQL, Go, C++, Java), or with Machine Learning, Anomaly Detection, or AI models.
Preferred
Master's degree or PhD in a technical field. Experience building and deploying anti-abuse systems at the scale of Google Cloud or Workspace. Experience in exploratory data analysis and statistical analysis with a track record of identifying non-obvious patterns in datasets. Ability to navigate ambiguity and solve problems in the AI safety domain. Excellent problem-solving and critical thinking skills with attention to detail in an ever-changing environment. Excellent written and verbal communication skills, with the ability to articulate technical safety concerns to executive leadership.