If you've ever looked at a system and immediately started thinking about how to break it — this role was made for you. We're looking for security-minded professionals to stress-test AI systems, expose their weaknesses, and help build the next generation of safe, reliable AI.
This is a fully remote, versatile contract role where your findings directly shape how AI behaves in the real world.
• Design and execute red-teaming exercises to uncover security weaknesses in AI systems
• Craft adversarial prompts and edge-case scenarios to probe model guardrails and safety filters
• Evaluate AI outputs for unsafe behavior, bias, and policy violations
• Document vulnerabilities, exploits, and unexpected behaviors in clear, structured reports
• Collaborate with engineering teams to recommend practical mitigations and improvements
• Stay current on emerging AI security threats, jailbreak techniques, and adversarial research
• Help define and refine security evaluation rubrics and testing protocols
Who You Are
• Strong understanding of cybersecurity concepts — threat modeling, penetration testing, or ethical hacking
• Hands-on experience with AI/ML systems, large language models, or prompt engineering
• Creative and analytical — you enjoy finding the edge cases others miss
• Excellent written communication and documentation skills
• Comfortable working independently in an asynchronous, task-based workplace
• Familiarity with open-source AI platforms or LLM ecosystems is a plus
• Background in infosec, AI safety research, or adversarial ML is a bonus — but not required
Why Join Us
• Work at the cutting edge of AI security alongside top research labs
• See your work directly improve the safety of AI products used by millions of people
• Full autonomy and a adaptable schedule — work when and how you work best
• Build deep, marketable expertise in
📌 Ai Red Team Tester Bengaluru
🏢 Alignerr
📍 Bengaluru
Reply to this offer
Impress this employer describing Your skills and abilities, fill out the form below and leave Your personal touch in the presentation letter.