Senior AI Safety Researcher

• Develop scalable safety solutions for AI products across Google by leveraging advanced machine learning and AI techniques.
• Apply statistical and data science methods to thoroughly examine Google's protection measures, uncover potential shortcomings, and develop actionable insights for continuous security enhancement.
• Drive business outcomes by crafting compelling data stories for a variety of stakeholders, including senior leadership.
• Provide technical leadership by fostering growth and ensuring success of junior team members through targeted mentorship and guidance.
• Be exposed to graphic, controversial, or upsetting topics or content as this role works with sensitive content or situations. 

Minimum qualifications:

• Bachelor's degree or equivalent practical experience.
  
• 5 years of experience in data analysis, including identifying trends, generating summary statistics, and drawing insights from quantitative and qualitative data.
  
• 5 years of experience in a data analysis or data science setting.
• Experience in programming languages (e.g., C/C++, Python, Java) and database languages (e.g., SQL).

Preferred qualifications:

• Master’s or Ph.D. degree in a quantitative discipline (e.g., Computer Science, Statistics, Mathematics, Operations Research etc.).
• Prior experience trust, safety, abuse, or fraud disciplines, especially focused on web security, harmful content moderation, and threat analysis.
• Experience with prompt engineering and fine-tuning LLMs.
  
• Proficient in developing and deploying machine learning models at scale.
• Excellent problem-solving and critical thinking skills with attention to detail in an ever-changing environment.
• Strong written, verbal, and presentation skills to effectively communicate with a variety of stakeholders, including executive leadership.
  

The AI Safety Protections team within Trust and Safety develops and implements AI-powered solutions to ensure the safety of foundation models, including Gemini, Veo, Agents, and Robotics. We work with DeepMind as well as downstream products such as enterprise (Vertex AI), on-device applications, and more.

We are a passionate team of data scientists and machine learning experts dedicated to mitigating risks associated with generative AI. As a member of our team, you will have the opportunity to apply the latest advancements in AI, work with teams across the company to develop cutting edge AI solutions, and protect people from real-world harms.

Google's foundation models are getting more capable fast, which can also introduce more severe harm if they're misused or unaligned. In this role, you will understand these frontier risks in depth and build safeguards against them. You will sit between research, model development, and policy. You will turn threat models into evaluations, mitigations, and launch decisions.

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

US: $159000 - $230000 (USD) + 15% bonus target + equity + benefits

Learn more about benefits at Google.In 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

• Bachelor's degree or equivalent practical experience.
  
• 5 years of experience in data analysis, including identifying trends, generating summary statistics, and drawing insights from quantitative and qualitative data.
  
• 5 years of experience in a data analysis or data science setting.
• Experience in programming languages (e.g., C/C++, Python, Java) and database languages (e.g., SQL).