Senior AI Security Engineer

We are seeking an experienced Senior AI Security Engineer to join our security team. This role will be responsible for ensuring the security, privacy, and integrity of our AI and machine learning systems, safeguarding them against evolving threats. You will collaborate with data scientists, AI/ML engineers, and other stakeholders to establish robust security best practices throughout the lifecycle of AI/ML model development, deployment, and maintenance.

What you'll do:

• Secure AI/ML Systems:Design, implement, and review security controls specifically tailored for AI and ML environments.
• Threat Modeling:Conduct comprehensive threat modeling and risk assessments for AI/ML systems, identifying potential vulnerabilities unique to AI technologies.
• Incident Response:Lead investigations into security incidents involving AI/ML models, recommend and implement improvements, and participate in post-mortems.
• Security Architecture:Collaborate on developing secure architectures for AI solutions including data collection, data labeling, model training, deployment, and inferencing.
• Secure Data Practices:Establish and enforce secure protocols for training data, ensuring privacy, integrity, and compliance with legal and regulatory guidelines.
• Red Teaming & Adversarial Testing:Simulate attacks (e.g., adversarial machine learning, model theft, data poisoning) and develop mitigation strategies.
• Automation and Tools:Build and maintain security tools for continuous monitoring, testing, and validation of AI/ML systems.
• Awareness and Training:Drive internal awareness programs and provide training for engineering, product, and data science teams on secure AI development.
• Compliance and Best Practice:Ensure companys AI initiatives comply with relevant industry standards and regulations (e.g., GDPR, CCPA, NIST AI Risk Management).
• Research and Development:Stay current with latest threats and advancements in AI security; propose innovative solutions to emerging risks.
• AI Agent Development: Contribute to building secure and intelligent AI bots/agents, ensuring best practices are followed during design and deployment.
• Development & Tools: Leverage Visual Studio and related development tools to support secure coding, debugging, and integration of AI systems.
• MCP Integration: Apply Model Control Protocol (MCP) knowledge to manage, orchestrate, and securely control AI/ML models across different environments.

What you'll bring:

• Bachelors or Masters Degree in Computer Science, Information Security, Data Science, or related field.
• 5+ years of experience in security engineering, with at least 2 years focused on AI/ML systems.
• Deep understanding of AI/ML development lifecycle and typical vulnerabilities (model inversion, adversarial attacks, data poisoning, etc.).
• Hands-on experience with AI/ML frameworks and security tools (e.g., TensorFlow, PyTorch, IBM Adversarial Robustness Toolbox).
• Proficiency in at least one programming language (Python preferred; C/C++ and Java are a plus).
• Strong knowledge of secure coding principles, cryptography, network security, and privacy-enhancing technologies.
• Experience with cloud-native AI platforms (AWS SageMaker, Azure ML, GCP AI Platform) and securing them.
• Familiarity with regulatory/compliance requirements relevant to AI/ML (GDPR, CCPA, HIPAA, etc.).
• Excellent analytical, communication, and teamwork skills.
• Published research or contributions to open source in the AI security domain.
• Security certifications (e.g., CISSP, OSCP, GCP/AWS Professional Security Engineer).
• Experience with MLOps and DevSecOps pipelines.
• Background in data privacy and ethical AI principles.