The Sr. AI Security Lead / AI Security Lead will be responsible for conducting advanced technical research, performing adversarial evaluations, developing AI security testing methodologies, and supporting the implementation of security controls within AI models and pipelines to ensure resilience against adversarial, manipulation, and exploitation threats. This role focuses on designing and executing AI security experiments, identifying vulnerabilities, supporting the development of defensive mechanisms, contributing technical insights to AI security tooling, and collaborating with engineering, Responsible AI teams, and security specialists to improve model robustness, safety, and secure deployment within the R&D environment.
AI Security Evaluations:
Conduct structured adversarial testing, vulnerability analysis, and security assessments on AI models, datasets, and pipelines to identify technical weaknesses.
2. Design AI Security Testing Methodologies:
Develop evaluation strategies, attack simulations, and test cases that examine model behavior under adversarial and stress conditions.
3. Analyze Model Vulnerabilities:
Review model outputs, logs, and error patterns to detect indicators of poisoning, evasion, extraction attempts, or unsafe behavior requiring mitigation.
4. Support Development of AI Defense Mechanisms:
Contribute technical insights for designing and implementing guardrail components, safety filters, validation controls, and secure model behavior constraints.
5. Conduct Research on Emerging AI Threats:
Study new attack surfaces such as prompt injection, model inversion, indirect influence attacks, and supply chain vulnerabilities relevant to modern AI systems.
6. Build Security Testing Scripts and Pipelines:
Create and maintain scripts, automation tasks, and evaluation pipelines that streamline security testing, red team simulations, and model behavior monitoring.
7. Document AI Security Findings:
Prepare technical reports, vulnerability summaries, experiment results, and evidence artifacts that support security reviews and R&D decision-making.
8. Collaborate with Cross Functional Teams:
Work with engineering, Responsible AI, cybersecurity, and data science teams to jointly investigate issues and integrate necessary security improvements.
9. Secure Model Deployment Activities:
Assist in validating the security posture of models before deployment by verifying guardrail integration, access controls, and vulnerability remediation.
10. Monitor Emerging AI Security Tools and Techniques:
Continuously evaluate new defensive methods, adversarial testing libraries, and AI security research to enhance testing capabilities and inform tooling upgrades.
Source: Infosys careers — Read the original posting and apply
This role is listed by the employer on its own careers site. Kaam Ki Khoj does not process applications for it.
Infosys is an employer in the IT/Computers - Software, Software Services sector with operations in India. This is a directory listing maintained by Kaam Ki Khoj so that candidates can find the organisation; it is not an official company page and Kaam... Read More
Upload your CV once — we read it, build your profile and put you in front of every employer hiring on Kaam Ki Khoj. No forms, no fees.
