LLM Red Team Specialist (Remote)

About the role

The LLM Red Team Specialist will join a remote AI‑safety team to rigorously test conversational models and agents. You will uncover vulnerabilities through jailbreaks, prompt injections, bias exploitation and multi‑turn manipulation, helping to make large language models safer for users worldwide.

Key responsibilities

• Red‑team LLMs and conversational agents using jailbreaks, prompt injections, misuse scenarios, bias exploitation and multi‑turn manipulation techniques.
• Generate high‑quality annotated data by classifying vulnerabilities, flagging systemic risks and documenting failure modes.
• Apply structured frameworks, taxonomies and benchmarks to ensure consistent, reproducible testing across projects.
• Produce clear, actionable reports, datasets and attack cases for both technical and non‑technical stakeholders.

Required profile

• Proven experience in adversarial testing, red‑team operations or socio‑technical probing of large language models or conversational systems.
• Strong background in cybersecurity disciplines such as penetration testing, exploit development or reverse engineering.
• Demonstrated ability to create structured documentation and communicate risk findings to diverse audiences.
• Native fluency in both English and Urdu.

Required skills

• Adversarial testing
• Red teaming
• Penetration testing
• Exploit development
• Reverse engineering

What we offer

• Hourly contract with flexible scheduling.
• Fully remote work environment.