AI Safety Specialist – Remote (up to $22/hr)

About the role

We are looking for an AI Safety Specialist to red‑team conversational AI models and agents. The role is fully remote and focuses on identifying and mitigating security, bias, and misuse risks in cutting‑edge AI systems.

Key responsibilities

• Red‑team conversational AI models and agents, performing jailbreaks, prompt injections, misuse case simulations, and bias exploitation.
• Generate high‑quality human 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 produce detailed reports, datasets, and attack cases for customer action.

Required profile

• Fluent in English and Punjabi.
• Prior experience in AI red‑team or adversarial work, cybersecurity, or socio‑technical probing.
• Strong communication skills to explain risks to both technical and non‑technical stakeholders.
• Adaptable and able to move across multiple projects and customers.

Required skills

• Adversarial machine learning (jailbreak dataset creation, prompt injection, RLHF/DPO attacks, model extraction).
• Penetration testing, exploit development, and reverse engineering.
• Socio‑technical risk analysis (harassment, disinformation, abuse probing) and creative probing techniques.

What we offer

• Hourly compensation of $20–$22.
• Fully remote contract position.