Senior Security Engineer – AI Security

• integrate security practices into DevOps pipelines across the SDLC
• automate security testing in CI/CD pipelines using tools like SonarQube, Checkmarx, Snyk
• implement Infrastructure as Code (IaC) security with Terraform, AWS CloudFormation
• embed security controls into automated deployment workflows
• conduct security assessments of enterprise and AI applications
• perform static/dynamic code analysis and runtime behavior assessments
• regularly scan for vulnerabilities and manage remediation
• evaluate third-party and open-source components for risk
• design secure architectures for enterprise and AI/ML applications
• create and maintain security reference architectures and design patterns
• evaluate and recommend tools and technologies to improve security posture
• address data protection, IAM, and secure communication in system designs
• perform in-depth threat modeling using STRIDE and similar methodologies
• use tools like Microsoft Threat Modeling Tool to analyze potential threats
• execute pen tests on AI/GenAI systems to uncover vulnerabilities
• simulate adversarial attacks like data poisoning, evasion, prompt injection
• use tools like CleverHans, SecML for adversarial robustness testing
• work closely with AI teams to fix vulnerabilities and harden models

• 5+ years in security engineering, including enterprise and AI security
• strong Cloud Security and DevSecOps implementation background
• proven experience in security assessments, threat modeling, and pen testing
• solid experience designing secure full-stack application and AI solutions
• Bachelor's or Master’s degree in Computer Science, Cybersecurity, or related
• certifications: CISSP, CEH, OSCP
• bonus: specialized AI/ML security certifications or training
• advanced proficiency with TensorFlow, PyTorch, and scikit learn
• strong Python programming skills
• experience implementing adversarial attack and defense techniques
• experience in identifying and mitigating vulnerabilities in large language models (LLMs)
• solid understanding of MLOps tools (Kubeflow, MLflow) and secure CI/CD pipeline practices for AI systems
• knowledge of legal and compliance standards relevant to AI security and data privacy

specialized AI/ML security certifications or training

• continuous professional development
• flexible working
• opportunities to grow within an inclusive and diverse environment