AI & Machine Learning Security Engineer

monitoring. - Identify and mitigate AI-specific vulnerabilities such as prompt injection, model poisoning, evasion attacks, and data leakage. AI-Driven Cyber Defense - Integrate AI-driven detection and automation capabilities into Cyber Defense Operations and SOC environments. - Develop AI/ML models to improve threat detection accuracy and automate incident response workflows. - Collaborate with Digital and AI teams to establish secure AI design patterns and responsible AI adoption standards. Governance & Guardrails - Define and implement AI security guardrails, technical standards, and control frameworks for enterprise-wide use cases. - Align AI security controls with emerging regulatory requirements, ethical AI principles, and risk obligations. - Conduct security assessments on internal and third-party AI/ML models and their underlying infrastructure. Tools & Technologies: - AI/ML Frameworks: Familiarity with PyTorch, TensorFlow, Scikit-learn, or Hugging Face. - LLM Security

Experience with tools like Giskard, Lakera, or OWASP Top 10 for LLMs. - Cloud AI Services: AWS SageMaker, Azure AI/ML Studio, or Google Vertex AI. - Security Tooling: Prompt injection filters, model monitoring tools, and adversarial robustness libraries (e.g., CleverHans, ART). - Container Security: Docker and Kubernetes (K8s) for ML workloads. What you bring: - 6-8+ years in Cybersecurity, focused on securing AI/ML workloads or using Data Science for security. - Technical Depth: Ability to analyze model architectures and data flows to identify security weaknesses. - Adversarial Mindset: Understanding of how attackers exploit ML models and how to build defensive “guardrails.” - Collaboration Skills: Proven experience working with Data Scientists and AI Engineers to bridge the gap between “speed to market” and “secure by design.” Equal Opportunity Employer: AspenView is proud to be an equal opportunity employer. We believe in creating an environment where all employees feel