Opportunity type
Internship
Cause areas
AI safety & policy
Routes to impact
Direct high impact on an important cause
Skill-building & building career capital
Testing your fit for a certain career path
Skill set
Research
Software engineering
Information security
Location
San Jose, CA
Description
HydroX AI is seeking a full-time, on-site AI Agent Security Intern (PhD) in San Jose, CA to research and develop safeguards for the safety, robustness, and security of advanced AI agents.
- Conduct research and experiments on agent failure modes, adversarial behaviors, and security vulnerabilities in AI agents.
- Build benchmarks, evaluation pipelines, and automated red-teaming systems for agentic workflows.
- Develop prototype safeguards such as runtime monitors, policy guardrails, and action filtering systems.
- Collaborate with experienced researchers and engineers from leading tech companies in a fast-paced startup environment.
Applicants must be PhD students in a relevant technical field and able to work on-site in San Jose, CA. Visa requirements are not specified.
This text was generated by AI. If you notice any inconsistencies, please let us know using this form
Join 60k subscribers and sign up for the EA Newsletter, a monthly email with the latest ideas and opportunities