About the role#
As an AI/ML Computational Scientist Intern on the AI Safety team, you will focus on the security and governance of real-world AI systems. You will work to ensure that AI deployments are reliable, secure, and aligned with enterprise standards as they move from prototype to production.
What you'll need#
- Enrollment in or expectation to enroll in a Master's or PhD program in Computer Science, Data Science, Mathematics, Statistics, Computer Engineering, or Electrical Engineering.
- At least 3 years of experience in AI agent security, safety evaluation, adversarial testing, and attack simulation.
- A minimum of 3 years of total experience, which may include prior internships or research.
- Note that this position does not offer visa sponsorship.
What you'll do#
- Evaluate and secure AI systems using advanced analytical and research skills.
- Develop methods to assess AI readiness, impact, and behavior, including the remediation of bias.
- Build safety features into offerings, such as runtime protection, agent safeguards, monitoring, and incident readiness protocols.
- Create data flywheels that transform real-world interaction data and adversarial signals into improvements for AI agents.
- Connect enterprise usage patterns back to model development to improve system reliability.
Location & details#
- Location: Mountain View, California.
- Modality: On-site.
- Employment: Full-time.
- Term: Rolling.


