Threat Modelling & Red Teaming Security Engineer

Mphasis; Bengaluru; On-site; INR 1,200,000 - 2,000,000; Full time

Job summary

A leading company is seeking an AI/ML Security Engineer to enhance the security of AI applications. This role involves designing governance frameworks and conducting threat assessments to protect AI models from vulnerabilities. Candidates should possess strong expertise in AI security and demonstrate exceptional problem-solving abilities. Familiarity with Python and AI libraries is essential, along with experience in Threat Modeling and Red Teaming.

Qualifications

• Proven experience in AI/ML security and governance.
• Strong knowledge of AI Governance frameworks.
• Expertise in Threat Modeling techniques.

Responsibilities

• Design and implement AI Governance frameworks.
• Conduct Threat Modeling to identify vulnerabilities.
• Perform Red Teaming exercises on AI systems.

Skills

AI/ML security

Threat Modeling

Red Teaming

Problem-solving

Python

Tools

TensorFlow

PyTorch

Scikit-learn

Job description

Threat Modelling & Red Teaming Security Engineer

Threat Modelling & Red Teaming Security Engineer

We are seeking a highly skilled and motivated AI/ML Security Engineer to join our cutting-edge security team. You will be responsible for ensuring the security and governance of AI/ML models and systems, focusing on AI Governance, Threat Modeling, and Red Teaming. Your expertise will help safeguard critical AI applications from potential threats and vulnerabilities while establishing robust governance practices.

Key Responsibilities

• Design and implement AI Governance frameworks to ensure security, compliance, and ethical use of AI models
• Conduct Threat Modeling to identify vulnerabilities within AI/ML pipelines and develop mitigation strategies
• Perform Red Teaming exercises to simulate real-world attacks on AI systems and evaluate their resilience
• Collaborate with data scientists and ML engineers to build secure AI models that resist adversarial attacks
• Develop and maintain security policies and best practices related to AI/ML applications
• Monitor and assess AI model behavior to detect anomalies and potential security breaches
• Stay up-to-date with the latest threats and vulnerabilities specific to AI/ML systems
• Document and communicate findings to stakeholders, including detailed technical reports and recommendations

Skills and Qualifications

Must-Have:

• Proven experience in AI/ML security and governance
• Strong knowledge of AI Governance frameworks and risk management practices
• Expertise in Threat Modeling techniques for AI/ML pipelines
• Proficiency in conducting Red Teaming exercises with a focus on AI systems
• Hands-on experience with Python and libraries related to AI and security (e.g., TensorFlow, PyTorch, Scikit-learn)
• Familiarity with adversarial attack techniques and defense mechanisms in ML models
• Solid understanding of cybersecurity principles and secure coding practices
• Excellent problem-solving skills and the ability to analyze complex security scenarios

Good to Have:

• Experience with ML model explainability and interpretability techniques
• Familiarity with security frameworks like NIST and ISO related to AI/ML governance
• Knowledge of cloud security (AWS, Azure, or GCP) related to AI deployments
• Strong analytical and technical writing skills for documenting findings and solutions

Seniority level

• Seniority level

  Mid-Senior level

Employment type

• Employment type

  Full-time

Job function

• Industries

  IT Services and IT Consulting, Software Development, and IT System Custom Software Development

Referrals increase your chances of interviewing at Mphasis by 2x

Get notified about new Security Engineer jobs in Bengaluru, Karnataka, India.

Security Engineer, Cloud Threat and Abuse Detection

Security Analyst, Cloud Threat detection

Senior Security Analyst, Cloud Threat Detection

HDFC Securities - Technical Lead - Site Reliability

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.