Job Summary
Develop and maintain safety protocols that surface gaps in model behavior, then translate findings into improvements to post-training. Advance model optimization and alignment methods, working across teams to support dependable agent performance.
Responsibilities
- Create and maintain protocols for assessing model safety and identifying behavioral weaknesses.
- Apply evaluation insights to inform and improve post-training processes.
- Explore and develop approaches to model optimization and alignment.
- Collaborate with cross-functional partners to promote reliable performance in AI agents.
Qualifications
- Bachelor’s degree or equivalent practical experience.
- At least two years of experience in software development or machine learning research.
- Expertise in machine learning algorithms, deep learning, and large language models.
Google provides equal employment opportunities to all employees and applicants for employment and prohibits discrimination and harassment of any type without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state or local laws.


