Role OverviewMercor connects elite creative and technical talent with leading AI research labs. As an AI Safety Expert - Red Team, you will be responsible for red teaming conversational AI models and agents to identify jailbreaks, prompt injections, misuse cases, and bias exploitation.
What You Will Do
Your responsibilities will include generating high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks. You will also apply structure by following taxonomies, benchmarks, and playbooks to maintain consistent testing, and document reproducibly by producing reports, datasets, and attack cases that customers can act on.
Why It Might Be a Fit
We are looking for someone with a curious and adversarial mindset, who can push systems to breaking points. You should have strong communication skills to explain risks to technical and non-technical stakeholders, and be adaptable to move across projects and customers.
Requirements
- Fluent Language Skills: English & Assamese
- Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
- Ability to push systems to breaking points with a curious and adversarial mindset
- Structured approach using frameworks or benchmarks
- Strong communication skills to explain risks to technical and non-technical stakeholders
- Adaptability to move across projects and customers
]]>