We are seeking an experienced Inbound LLM Red Team Specialist focused on identifying failure modes and edge cases in large language models. This role is based in the USA and requires a professional with 2 to 10 years of relevant experience.
Responsibilities:
- Analyze and test large language models to discover vulnerabilities, failure modes, and edge cases.
- Develop and execute red teaming strategies to improve model robustness and safety.
- Collaborate with cross-functional teams to communicate findings and recommend mitigations.
- Continuously monitor model behavior and contribute to enhancing overall system reliability.
Requirements:
- 2 to 10 years of experience working with large language models or related AI systems.
- Strong analytical skills focused on identifying complex failure scenarios.
- Ability to design and implement red team testing methodologies.
- Excellent communication skills to document and present findings effectively.