Content Safety Analyst – Remote (AI Red Teaming)

About the role

We are seeking experienced AI safety experts fluent in English and Bengali to join our remote team on a contract basis. The role involves 10‑40 hours per week of focused red‑team testing on conversational AI models and agents, with compensation ranging from $20 to $22 per hour.

Key responsibilities

• Red‑team conversational AI systems by executing jailbreaks, prompt injections, and bias exploitation.
• Generate high‑quality human data through failure annotation, vulnerability classification, and systemic risk flagging.
• Apply structured methodologies using taxonomies, benchmarks, and playbooks to ensure consistent testing.
• Document findings reproducibly by creating reports, datasets, and attack cases for customer action.

Required profile

• Prior red‑team experience in AI adversarial work, cybersecurity, or socio‑technical probing.
• Curiosity and an adversarial mindset, capable of pushing systems to their breaking points.
• Structured approach using frameworks or benchmarks rather than random hacks.
• Strong communication skills to explain risks to both technical and non‑technical stakeholders.
• Adaptability and ability to move across various projects and customers.

Required skills

• AI adversarial red‑team testing
• Cybersecurity fundamentals

What we offer

• Flexible remote work schedule (10‑40 hrs/week).
• Competitive hourly rate ($20‑$22).
• Opportunity to work on cutting‑edge AI safety challenges.