AI Security Engineer (M/F/D)

Why this job matters

Your responsibilities

• AI Security Controls Implementation
• Onboard and implement AI-specific security controls to bridge xBU AI security risks
• Develop and deploy technical safeguards against AI-specific threats (e.g., prompt injection, data poisoning, model extraction, adversarial attacks)
• Design and maintain security guardrails for Large Language Models (LLMs) and other AI systems
• Establish secure AI development pipelines and deployment practices
• AI POC Facilitation & Acceleration
• Facilitate and fast-track AI Proof of Concepts (POCs) by providing security guidance from inception, define PoC use cases, testing scenarios, execute those, evaluate product capabilities an capabilities maturity.
• Create reusable security patterns, templates, and toolkits for common AI use cases
• Collaborate with AI development teams to embed security into the AI lifecycle
• Streamline security review processes for AI initiatives to reduce time-to-market
• Advise on pragmatic, risk-balanced solutions that enable faster deployment without compromising security posture
• Risk Evaluation & Capability Incubation
• Evaluate alternative solutions when security red flags are raised during AI projects.
• Conduct security assessments and threat modeling for AI systems.
• Incubate AI security capabilities in partnership with IT and Security practitioners
• Drive knowledge transfer and upskilling of security teams on AI-specific threats and controls
• Contribute to the development of AI security standards, policies, and best practices

Job Skills/Competencies Required

Your profile

• Bachelor's or Master's degree in Computer Science, Cybersecurity, or related field.
• 3-5 years of experience in security engineering / development, cybersecurity, application security, or related fields.
• 2+ years of hands-on experience with AI/ML technologies and their security implications
• Experience implementing AI security controls in cloud environments (e.g. AWS - AWS Bedrock Guardrails, Azure - Prompt Shields, GCP - Vertex AI Model Armor)
• Experience with AI security tools (e.g. Garak, PyRIT, Promptfoo, langsmith, etc. )
• Experience with AI security frameworks and guidelines (OWASP, NIST AI RMF, etc.)
• Knowledge of AI-specific vulnerabilities and attack vectors (prompt injection, jailbreaking, data leakage, etc.), mitigations and controls effectiveness.
• Strong understanding of AI/ML technologies, including LLMs, DNNs, and prompt engineering.
• Familiarity with AI/ML frameworks (TensorFlow, PyTorch, Hugging Face, LangChain, etc.)
• Excellent coding and scripting skills and ability to develop robust custom tools and automation (Python, JavaScript, etc.)
• Excellent English language skills.
• Excellent communication and presentational skills