AI Systems Red Teamer | Remote

AI Safety Red Teamer English & Kannada

Work Snapshot Type: Hourly Contract

Commitment: Flexible schedule; project-based with potential for extension

What You'll Be Doing

• Red team conversational models and agents across jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation
• Generate high-quality annotated data by classifying vulnerabilities, flagging systemic risks, and documenting failure modes
• Apply structured frameworks, taxonomies, and benchmarks to ensure consistent, reproducible testing coverage
• Produce clear reports, datasets, and attack cases that enable customers to act on identified risks
• Probe systems for socio-technical vulnerabilities including misinformation vectors, harassment patterns, and abuse scenarios

What We're Looking For

• Strong experience in adversarial testing, red teaming, or cybersecurity including penetration testing, prompt injection, or socio-technical risk analysis
• Strong experience working with LLMs or conversational systems in an adversarial or evaluative capacity
• Strong experience documenting and communicating risk findings to both technical and non-technical audiences
• Native fluency in both English and Kannada is required
• Structured, framework-driven approach to testing not ad hoc; able to apply benchmarks and playbooks consistently

How To Apply

• Upload resume
• Submit form