AI Security Researcher at Robust Intelligence

Are you ready to help shape the future of secure, trustworthy AI? At Robust Intelligence, our mission is to enable every organization on the planet to adopt AI securely. As AI systems become central to automated decision-making, new risks emerge from both unintentional errors and deliberate attacks. Our flagship product integrates with existing AI systems to identify and eliminate these risks, and our Generative AI Firewall now protects against the latest vulnerabilities that threaten AI companies and their users. We have assembled a multidisciplinary team of ML engineers, AI security specialists, and software engineers who are building the next generation of AI defenses together.

What you bring

We are looking for a senior professional to join us full time in a remote capacity. In this role you will track and analyze emerging threats to AI and machine-learning systems, develop detection and mitigation strategies that include rapid prototyping, and lead red-teaming exercises that uncover vulnerabilities in generative AI technologies. You will also build and maintain security tools and frameworks in Python or Golang, curate high-quality datasets for training ML models, and publish research findings through blog posts, white papers, or academic papers. The position is open to candidates located anywhere.

• Track and analyze emerging threats to AI systems, focusing on AI/ML models, applications, and environments.
• Develop and implement detection and mitigation strategies for identified threats, including prototyping new approaches.
• Lead comprehensive red-teaming exercises and vulnerability assessments for generative AI technologies, identifying and addressing potential security vulnerabilities.

Requirements

You bring at least three years of hands-on experience in applied red-team or blue-team roles such as threat intelligence, threat hunting, or red teaming. You have a strong grasp of common application security vulnerabilities and their mitigations, along with solid programming skills in Python or Golang. Excellent written and verbal communication, sharp analytical thinking, and proven problem-solving abilities are essential. You learn new technologies quickly and can translate a wide range of technical challenges into practical solutions. We value candidates who have explored AI/ML-specific risks such as data poisoning, privacy attacks, and adversarial inputs, who can read and prototype ideas from academic papers, and who have experience with modern application stacks and proof-of-concept exploit development. English proficiency is required.

What we offer

We provide a competitive salary, meaningful equity ownership, market-leading health, dental, and vision insurance for employees and dependents, a flexible time-off policy, paid parental and family leave, a child-care allowance, a 401(k) retirement plan, commuter benefits, immigration sponsorship for H-1B visas and green cards, an education reimbursement program, daily catered lunches and dinners when working late, stocked kitchens, an on-site gym, and a wellness program.

• Remote work
• 401(k) retirement plan
• Commuter benefits

How to Apply

If this opportunity excites you, we encourage you to apply even if you do not meet every single qualification. We value diverse backgrounds and perspectives and look forward to learning how your experience can contribute to our mission.