Security Engineer – AI Security

Security Engineer – AI Security
Location: Bengaluru, India
Function: AI Security – Technology & Innovation Centre (TIC)
Employment Type: Full-time
Role Purpose
The Security Engineer – AI Security is responsible for identifying, analysing, and
mitigating security risks across AI systems, models, and pipelines. The role focuses on
applying security engineering principles to AI-specific threats, validating security
controls, and ensuring robustness, compliance, and trustworthiness of AI-enabled
systems.
Key Responsibilities
- Assess security risks in AI models, data pipelines, and deployment environments.
- Design and execute security testing for AI systems, including misuse, backdoors, and
anomalous behaviour.
- Collaborate with researchers to evaluate model vulnerabilities and security
assumptions.
- Support validation of AI security controls such as scanning, verification, and unlearning
mechanisms.
- Contribute to AI threat modelling, abuse case definition, and mitigation strategies.
- Review system designs to ensure compliance with security and privacy requirements.
- Support investigation and remediation of AI-related security incidents.
Required Technical Skills
- Strong background in security engineering and applied cybersecurity.
- Understanding of AI/ML systems and common AI-specific threat vectors.
- Experience with security testing, threat modelling, and risk assessment.
- Familiarity with AI security techniques such as model analysis, anomaly detection, or
behaviour testing.
- Knowledge of secure system design, access control, and compliance considerations.
- Strong scripting or programming skills (Python or similar).
Qualifications & Experience
Education:
- Bachelor’s or Master’s degree in Computer Science, Cybersecurity, Engineering, or a
related field.
Experience:
- 5–8+ years of experience in security engineering, application security, or applied
cybersecurity roles.
- Exposure to ML or data-intensive systems is strongly preferred.
Success Indicators
- Timely identification and mitigation of AI security risks.
- Effective validation and strengthening of AI security controls.
- Improved security posture and resilience of AI systems and platforms.

Work arrangement
Hybrid