AI Security Engineer / Adversarial Machine Learning Researcher / Model Protection Specialist

Design, implement, and enhance security solutions that protect artificial intelligence (AI) systems, machine learning models, and Generative AI applications from emerging cyber threats, adversarial attacks, data manipulation, and unauthorized access.

This role is responsible for securing the entire AI lifecycle, strengthening model resilience, implementing AI governance frameworks, and ensuring AI technologies are deployed safely, responsibly, and in compliance with industry regulations.

The successful candidate will collaborate with AI researchers, machine learning engineers, cybersecurity teams, software engineers, cloud architects, Dev Sec Ops, data scientists, legal, compliance, product management, and cross-functional stakeholders to build secure and trustworthy AI systems.

The role also involves researching adversarial machine learning techniques, evaluating model vulnerabilities, securing large language models (LLMs), implementing retrieval-augmented generation (RAG) security controls, protecting training data, securing inference pipelines, developing AI threat detection capabilities, performing red team assessments, implementing AI security monitoring, leveraging artificial intelligence (AI)-powered security analytics, intelligent automation, cloud-native security, governance frameworks, risk management, and continuous improvements that strengthen AI resilience, safeguard enterprise AI assets, and support responsible AI innovation.

Qualifications

• Bachelor's degree in Computer Science, Artificial Intelligence, Cybersecurity, Information Security, Software Engineering, Data Science, Mathematics, Information Technology, or a related field; Master's degree or Ph.

D. in Artificial Intelligence, Machine Learning, Cybersecurity, or a related discipline is highly desirable.

• Proven experience as an AI Security Engineer, Adversarial Machine Learning Researcher, Model Protection Specialist, Machine Learning Security Engineer, AI Research Scientist, Security Researcher, AI Red Team Engineer, LLM Security Engineer, or a similar AI security role.
• Strong understanding of artificial intelligence, machine learning, Generative AI, large language models (LLMs), retrieval-augmented generation (RAG), adversarial machine learning, model poisoning, prompt injection, data poisoning, model inversion, model extraction, AI governance, secure software development lifecycle (SSDLC), Dev Sec Ops, and cloud security.
• Extensive experience designing secure AI architectures, performing AI security assessments, researching adversarial attacks, securing machine learning pipelines, implementing model monitoring, conducting penetration testing, building AI detection and response capabilities, deploying AI governance controls, and strengthening enterprise AI security.
• Hands-on experience with Python, SQL, Tensor Flow, Py Torch, Scikit-learn, Lang Chain, Llama Index, Hugging Face, Open AI APIs, Azure AI Foundry, Azure Machine Learning, Amazon Sage Maker, Google Vertex AI, Databricks, Snowflake, Kubernetes, Docker, MLflow, Git Hub, Git Lab, Terraform, Splunk, Microsoft Sentinel, Microsoft Defender, Crowd Strike, Wiz, Prisma Cloud, Palo Alto Networks, AWS, Microsoft Azure, Google Cloud Platform (GCP), and AI security platforms.
• Strong knowledge of secure AI model deployment, MLOps, AI model lifecycle management, cryptography, identity and access management (IAM), Zero Trust architecture, API security, container security, Infrastructure as Code (Ia C), AI risk management, explainable AI (XAI), privacy-preserving machine learning, differential privacy, federated learning, and regulatory compliance.
• Familiarity with artificial intelligence (AI), Generative AI, AI red teaming, AI safety evaluation, AI guardrails, AI observability, intelligent automation, behavioral analytics, threat intelligence, cloud-native security, predictive analytics, and emerging AI security technologies is highly desirable.
• Strong analytical, research, and problem-solving skills with the ability to identify AI vulnerabilities, evaluate security risks, design resilient AI architectures, optimize defensive controls, and provide strategic recommendations to technical and executive stakeholders.
• Excellent communication, presentation, collaboration, and stakeholder management skills with the ability to work effectively with AI researchers, software engineers, cybersecurity teams, cloud architects, compliance professionals, product managers, executive leadership, and external security partners.
• Experience supporting enterprise AI platforms, cloud-native AI services, cybersecurity operations, regulated industries, multinational technology organizations, research institutions, or large-scale AI transformation initiatives is highly desirable.
• Strong program and project management capabilities with experience managing AI security roadmaps, governance frameworks, enterprise AI risk programs, security assessments, cross-functional engineering teams, vendor relationships, and multiple concurrent AI initiatives.
• Professional certifications such as Certified Information Systems Security Professional (CISSP), Certified Cloud Security Professional (CCSP), Microsoft
• Certified: Cybersecurity Architect Expert, Microsoft

Certified: Azure AI Engineer Associate, AWS Certified Machine Learning - Specialty, Google Professional Machine Learning Engineer, Offensive Security Certified Professional (OSCP), GIAC Security Certifications, or equivalent AI, cloud, and cybersecurity certifications are considered an advantage.

• A highly innovative, security-focused, and research-driven AI professional with a passion for leveraging Generative AI, large language models (LLMs), adversarial machine learning research, automation, advanced analytics, cloud-native security, and modern AI protection technologies to build resilient AI systems, defend against evolving threats, enable responsible AI adoption, and deliver sustainable long-term business value.
• #J-18808-Ljbffr