AI Safety & Red Teaming Specialist
RemoteContract2–5 yrsPosted 4 months ago
Mid-level cybersecurity contract role at Weekday AI. Needs 2+ years and a PhD, M.Tech or MCA. Remote.
About the role
We are looking for an experienced AI Safety & Red Teaming Specialist to help evaluate and strengthen the safety, security, and robustness of next-generation AI systems. In this role, you will leverage your expertise in adversarial AI, LLM security, and AI safety to identify vulnerabilities, design evaluation methodologies, and improve the resilience of large language models against real-world threats.
What you'll do
- Design and implement advanced evaluation methodologies for AI system safety, including ethical jailbreak testing, prompt injection detection, LLM red teaming
- Develop cross-domain adversarial testing strategies to uncover complex, multi-turn attack patterns and model vulnerabilities
- Build, maintain, and enhance regression test suites to continuously assess jailbreak susceptibility and prompt injection risks
- Create comprehensive evaluation frameworks that simulate real-world adversarial threats to improve AI robustness and reliability
- Collaborate with technical teams to translate security findings into actionable recommendations for AI safety improvements
What you need
- LLMs
- Machine learning
- Prompt engineering
- Regression testing
- Penetration testing