AI Safety Expert - Red Teaming

About the role

We are looking for an AI Safety Expert to join our remote red‑teaming squad. You will work on exposing weaknesses in conversational AI models and agents, helping our clients improve robustness and mitigate misuse.

Key responsibilities

• Red‑team conversational AI systems by performing jailbreaks, prompt injections, bias exploitation and other misuse scenarios.
• Generate high‑quality human‑generated data, annotate failures, classify vulnerabilities and flag systemic risks.
• Apply structured taxonomies, benchmarks and playbooks to ensure consistent testing across projects.
• Document findings reproducibly and deliver detailed reports, datasets and attack cases for customer remediation.

Required profile

• Fluent in English and Punjabi.
• Proven experience in AI red‑teaming, adversarial security or socio‑technical probing.
• Strong written and verbal communication skills for both technical and non‑technical audiences.
• Adaptable and able to switch between multiple projects and customers.

Required skills

• Adversarial machine‑learning techniques such as jailbreak datasets, prompt injection, RLHF/DPO attacks and model extraction.
• Cyber‑security capabilities including penetration testing, exploit development and reverse engineering.
• Experience with socio‑technical risk analysis of harassment, disinformation and abuse in conversational AI.

What we offer

• Contract position paying $20–$22 per hour.
• Fully remote work with flexible hours.
• Opportunity to collaborate with leading AI research labs and impact cutting‑edge safety research.