AI Safety and Red Teaming Professional
We are seeking a highly analytical professional with hands-on experience in red teaming, prompt evaluation and AI/LLM quality assurance.
1. Conduct thorough red team exercises to identify adversarial outputs from large language models (LLMs).
2. Evaluate and stress-test AI prompts across multiple domains to uncover potential failure modes.
3. Develop test cases to assess accuracy, bias, toxicity and misuse potential in AI-generated responses.
4. Collaborate with data scientists to report risks and suggest mitigations.
5. Perform manual content validation across model versions to ensure consistency, coherence and guideline adherence.
Requirements:
* Proven experience in AI safety testing, LLM security or adversarial prompt design.
* Familiarity with prompt engineering, NLP tasks and ethical considerations in generative AI.
* Strong background in quality assurance, content review or test case development for AI/ML systems.
* Understanding of LLM behavior and failure modes.
Benefits: Collaborative work environment, flexible working hours and opportunities for professional growth.