This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for an AI Safety & Red Teaming Specialist based in India.
This role focuses on strengthening the safety, reliability, and resilience of next-generation AI systems through structured adversarial testing and evaluation. You will work at the intersection of AI security, large language models, and applied research to uncover vulnerabilities and improve system robustness. The environment is highly technical, fast-evolving, and deeply collaborative, involving close work with engineers and research teams. Your work will directly influence how AI systems respond to real-world adversarial scenarios. You will design and execute red teaming strategies that simulate malicious use cases, including prompt injection and jailbreak attempts. This is a high-impact opportunity for someone passionate about AI safety, ethical hacking, and building trustworthy AI systems at scale.
This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for an AI Safety & Red Teaming Specialist based in India.
This role focuses on strengthening the safety, reliability, and resilience of next-generation AI systems through structured adversarial testing and evaluation. You will work at the intersection of AI security, large language models, and applied research to uncover vulnerabilities and improve system robustness. The environment is highly technical, fast-evolving, and deeply collaborative, involving close work with engineers and research teams. Your work will directly influence how AI systems respond to real-world adversarial scenarios. You will design and execute red teaming strategies that simulate malicious use cases, including prompt injection and jailbreak attempts. This is a high-impact opportunity for someone passionate about AI safety, ethical hacking, and building trustworthy AI systems at scale.
Accountabilities:
- Design and implement AI safety evaluation frameworks, including jailbreak testing, prompt injection detection, and tool-use abuse scenarios
- Develop adversarial red teaming strategies to identify multi-turn vulnerabilities and complex attack patterns in LLM-based systems
- Build and maintain regression test suites to continuously assess model safety, robustness, and failure modes
- Simulate real-world adversarial behaviors to evaluate system resilience across different use cases and domains
- Collaborate with engineering and research teams to translate findings into actionable safety improvements
- Document methodologies, test results, and insights in clear technical reports for both technical and non-technical audiences
- 2+ years of experience in AI Safety, LLM Red Teaming, Adversarial Machine Learning, or AI Security
- Hands-on experience identifying or testing vulnerabilities such as prompt injection, jailbreaks, or model exploitation techniques
- Strong understanding of LLM architectures, prompt engineering, and evaluation methodologies for AI systems
- Experience building structured testing frameworks, regression suites, or adversarial evaluation pipelines
- Ability to analyze complex system behavior and clearly communicate technical findings and risks
- Strong collaboration skills with experience working in cross-functional technical teams
- (Preferred) Advanced degree in Computer Science, AI, Cybersecurity, or related field
- (Preferred) Exposure to research, open-source contributions, or published work in AI safety or security domains
- Competitive contractor compensation: $50 – $90 per hour, based on experience
- Fully remote role with flexibility in working arrangements
- Opportunity to work on cutting-edge AI safety and LLM security challenges
- High-impact role influencing real-world AI system reliability and trustworthiness
- Exposure to advanced AI research, red teaming methodologies, and production-scale systems
- Collaborative, research-driven environment focused on innovation and technical excellence.
In this role, you will be responsible for designing, executing, and documenting advanced safety and adversarial evaluations to strengthen AI system reliability and security.
Requirements:
We are looking for a technically strong and detail-oriented professional with hands-on experience in AI safety, adversarial ML, or LLM security, combined with strong communication and analytical skills.