AI Red Team Engineer
About This Role
We're seeking an AI Red Team Engineer to join our AI-first recruiting platform at a critical growth stage. In this role, you'll design and execute adversarial testing frameworks to identify vulnerabilities, biases, and failure modes in our AI/ML systems before they impact users. You'll collaborate with ML engineers and product teams to build robust, trustworthy AI systems that power our B2B SaaS recruiting platform. As an AI Red Team Engineer, you'll develop prompt injection tests, jailbreak scenarios, and adversarial examples to stress-test language models and classification systems. You'll document findings, propose mitigations, and help establish AI safety best practices across our engineering organization. This is a hands-on technical role combining security expertise, AI knowledge, and creative problem-solving.
Requirements
- Design and execute red team exercises targeting LLM and ML model vulnerabilities
- Develop adversarial prompts, jailbreak scenarios, and edge-case test suites
- Write production-grade Python code for automated testing frameworks
- Identify and document AI bias, fairness issues, and safety risks
- Collaborate with ML engineers to propose and validate mitigations
- Maintain security-first mindset with experience in adversarial machine learning or security testing