AI Safety Specialist (Remote) – $20–$22/hr

About the role

We are looking for an AI Safety Specialist to join our remote team and help secure conversational AI models. You will work on identifying and mitigating vulnerabilities through red‑team exercises, ensuring that AI agents behave safely and responsibly.

Key responsibilities

• Conduct red‑team attacks on conversational AI models, including jailbreaks, prompt injections and bias exploitation.
• Generate high‑quality human‑annotated data by documenting failures, classifying vulnerabilities and flagging systemic risks.
• Follow established taxonomies, benchmarks and playbooks to keep testing consistent and reproducible.
• Produce detailed reports, datasets and attack cases that customers can act on.
• Collaborate on sensitive projects while adhering to clear guidelines and wellness resources.

Required profile

• Native fluency in English and Tamil.
• Strong communication skills to explain technical risks to both technical and non‑technical audiences.
• Prior experience in red‑team or adversarial work within AI, cybersecurity or socio‑technical domains.

Required skills

• Red teaming of AI systems.
• Adversarial machine learning techniques.
• Cybersecurity fundamentals.

What we offer

• Contract position with hourly rate of $20–$22.
• Fully remote work arrangement.
• Access to wellness resources and clear project guidelines.