About this role
Role Overview
Help strengthen conversational AI systems by testing them like an adversary. You will probe models and agents with challenging inputs, uncover vulnerabilities, and create actionable red-team data that improves AI safety and reliability.
Key Responsibilities
- Test conversational AI models and agents for jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation.
- Review text-based AI outputs that may address sensitive topics, including bias, misinformation, and harmful behaviors.
- Annotate failures, classify vulnerabilities, and identify systemic risks.
- Use defined taxonomies, benchmarks, and playbooks to perform consistent testing.
- Create reproducible reports, datasets, and attack cases that teams can use to improve AI systems.
Qualifications
- Native fluency in both English and Odia is required.
- Prior experience in AI red teaming, cybersecurity, or socio-technical risk assessment.
- Ability to test systems methodically using frameworks or benchmarks and clearly communicate risks to technical and non-technical audiences.
- Comfort adapting across projects and client needs.
Preferred Experience
- Adversarial machine learning, including jailbreak datasets, prompt injection, RLHF or DPO attacks, or model extraction.
- Cybersecurity, including penetration testing, exploit development, or reverse engineering.
- Socio-technical risk testing, including harassment or misinformation probing, abuse analysis, or conversational AI testing.
- Psychology, acting, or writing that supports unconventional adversarial thinking.
Work Terms
- Remote, hourly engagement.
- All work is text-based.
- Participation in higher-sensitivity projects is optional. Topics will be communicated before exposure, with clear guidelines and wellness resources available.
Compensation
- $20 to $22 per hour.