Red Team Engineer, AI Product Safeguards
AI safety-focused public benefit corporation, headquartered in the Bay Area
| Employer | AI safety-focused public benefit corporation, headquartered in the Bay Area (not named) |
|---|---|
| Location | San Francisco, CA (Bay Area) · Hybrid |
| Type & level | Full-time · Senior |
| Pay | USD 320k–405k base Source: pay range stated in the source posting |
| Visa path | O-1A fit |
| Role family | AI Red Team / ML Security Researcher |
About the role
This role sits on a safeguards team that tests deployed AI products the way a real attacker would. The work covers classic application vulnerabilities as well as new abuse that only appears with advanced AI, such as agent and tool-use exploits. Findings go to product, engineering and policy teams so they can be fixed.
What you'll do
- Run adversarial tests across the company's product surfaces, combining several exploit techniques into realistic attack scenarios
- Plan and carry out full kill-chain exercises that imitate real threat actors pursuing specific malicious goals
- Develop new testing approaches for emerging capabilities such as agent systems and tool use
- Build automated testing frameworks so assessment can run continuously and at scale
- Investigate abuse patterns such as coordinated account manipulation and payment fraud
- Work with product, engineering and policy colleagues to turn findings into fixes and help define metrics for detecting novel abuse
Requirements
- Experience in penetration testing, red teaming or application security
- Experience with model jailbreaking and testing large agentic workflows for prompt injection vectors
- Strong web application security skills with tools such as Burp Suite, Metasploit and custom scripts
- Experience building custom automation, including LLM-specific testing frameworks
- A track record of finding novel attack vectors and chaining vulnerabilities, shown through public work such as CVEs, blog posts or bug bounty reports
- Bachelor's degree or equivalent combination of education, training and experience, plus strong written and verbal communication
Nice to have
- Experience with AI/ML security or adversarial machine learning
- Understanding of AI safety beyond traditional security, including modern jailbreak guardrails
- Experience testing API security and rate limiting, and business logic or authorization bypass flaws
- Background in anti-fraud, trust and safety, or abuse prevention
- Familiarity with distributed systems, infrastructure security and abuse detection mechanisms
Pay & benefits
USD 320k–405k base. The posting mentions competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, and flexible working hours. Staff are expected in an office at least 25 percent of the time.
Pay source: pay range stated in the source posting. Market data, not an offer from O1DMatch.
Visa path
People in AI red teaming and security research often support an O-1A case with a public body of work, such as disclosed CVEs, bug bounty reports, published research or talks, plus high compensation and expert recognition. The posting states no citizenship restriction and says the employer sponsors visas for some roles and candidates. An employer like this or a U.S. agent can file an O-1A petition, though approval depends on the individual's evidence.
How to get matched
- Take the free eligibility checkAn AI review of your background against the eight O-1 criteria, at check.o1dmatch.com.
- Create your profile with code WORKWITHUSIt unlocks the Starter plan at no cost. Tell us your field and the work you do today.
- Upload your evidenceEach document is sorted under the criterion it supports, and your criteria map shows what is still missing.
- Get matchedWe match strong profiles with U.S. employers hiring for roles like this one. Gigs you confirm with verified companies count toward your itinerary, and at a score of 75 we connect you with an immigration attorney.
This listing describes a real U.S. posting so you can see what employers ask for. O1DMatch does not represent that employer and does not hold this opening; applying matches you with employers hiring for this kind of role. No visa outcome is promised.