AI Safety & Red Teaming Specialist
New
IndiaContractMiddle
Salary50 - 90 USD per hour
Apply NowOpens the employer's application page
Job Details
- Experience
- 2+ years
- Required Skills
- Regression testingPrompt Engineering
Requirements
- 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.
- 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 (Preferred).
Responsibilities
- 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.
View Full Description & ApplyYou'll be redirected to the employer's site
