About the role#
As an AI/ML Computational Scientist intern on the AI Safety team, you will focus on the evaluation, security, and governance of real-world AI systems. This role involves bridging the gap between prototype and production by connecting enterprise usage back to model improvement. You will work on-site in Mountain View as part of a full-time, paid internship with a rolling term.
What you'll need#
- Current enrollment in or expected enrollment in a Master's or PhD program in Computer Science, Data Science, Mathematics, Statistics, or Physics.
- At least one year of experience in AI agent security, safety evaluation, adversarial testing, and attack simulation.
- A minimum of one year of experience, including prior research or internships.
- Authorization to work in the United States without the need for visa sponsorship.
What you'll do#
- Apply research and computational skills to secure and govern AI systems.
- Develop methods to evaluate AI deployments, assess readiness, and remediate bias or behavior failures.
- Integrate AI safety into offerings through runtime protection, agent safeguards, monitoring, and incident readiness.
- Build data flywheels that transform real-world interactions, failures, and adversarial signals into secure and reliable AI agents.
Location & details#
- Location: Mountain View, California.
- Work Modality: On-site.
- Employment Type: Full-time.


