What You’ll Be Doing
Red team conversational models and agents through jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation.
Generate high-quality annotated data by classifying vulnerabilities, flagging systemic risks, and documenting failure modes.
Apply structured frameworks, taxonomies, and benchmarks to ensure consistent and reproducible testing.
Produce clear reports, datasets, and attack cases that stakeholders can act on across technical and non-technical audiences.
What We’re Looking For
Strong experience in adversarial testing, red teaming, or socio-technical probing of LLMs or conversational systems.
Strong experience in cybersecurity disciplines such as penetration testing, exploit development, or reverse engineering.
Strong experience in structured documentation and communicating risk findings to diverse audiences.
Native fluency in both English and Urdu is required.