Senior AI Evaluation Lead — Methodology & Testing

Google; Atlanta (GA); Hybrid; USD 171,000 - 247,000; Full time

Benefits offered by this job

Health insurance

Retirement 401(k)

Paid time off

Sick time

Maternity leave

Baby bonding

Holiday pay

Job summary

Google is seeking an AI safety researcher within Trust and Safety to lead novel testing methodologies for emergent AI and to design evaluation frameworks for GenAI products. You will collaborate with data science and engineering teams to build scalable testing infrastructure and prototype experiments that identify systemic risks.

US-based candidates will enjoy a comprehensive benefits package, a competitive base salary, a 20% bonus target, equity, and paid time off with multiple US locations and

Qualifications

• Bachelor's degree or equivalent practical experience.
• 10 years of experience in AI testing or research, data analytics, data science, or a related field.
• Master's degree or PhD in relevant field preferred.
• 5 years of experience in data analysis for AI Testing with SQL or Python.
• Experience building prototypes and partnering with engineering teams.
• Experience designing experiments or quantitative research in AI contexts.
• Knowledge of AI systems, machine learning, and potential risks.
• Strong data-driven investigative skills with Python and SQL.

Responsibilities

• Drive methodological frontier of model evaluation with data-driven testing frameworks.
• Define testing and safety standards; develop model- and product-level mitigations.
• Lead cross-functional teams; advise executive leadership on safety issues.
• Represent Google's AI safety efforts in external forums and collaborations.
• Work with sensitive content; handle potentially upsetting topics.

Skills

Data analysis

Python

SQL

AI testing

Education

Bachelor's degree or equivalent practical experience

Master's degree or PhD in relevant field

Tools

Python

SQL

Job description

Google is seeking an AI safety researcher within Trust and Safety to lead novel testing methodologies for emergent AI and to design evaluation frameworks for GenAI products. You will collaborate with data science and engineering teams to build scalable testing infrastructure and prototype experiments that identify systemic risks.

US-based candidates will enjoy a comprehensive benefits package, a competitive base salary, a 20% bonus target, equity, and paid time off with multiple US locations and