Join an international organization where you will help build secure and scalable AI solutions while balancing innovation with real-world security requirements.
You will work with LLMs, AWS Bedrock Guardrails, Azure Prompt Shields, GCP Vertex AI Model Armor, Garak, PyRIT, Promptfoo, LangSmith, OWASP, NIST AI RMF, Python, and modern AI/ML frameworks.
- Implement AI-specific security controls and guardrails to protect LLMs and AI systems against threats such as prompt injection, data poisoning, model extraction, and data leakage
- Design and maintain secure AI development and deployment practices across cloud environments
- Support AI Proof of Concepts from the early stages by defining security requirements, testing scenarios, and practical risk controls
- Conduct security assessments and threat modeling for AI solutions and evaluate the security maturity of emerging technologies
- Create reusable security patterns, templates, and toolkits that help development teams integrate security throughout the AI lifecycle
- Act as an AI Security Subject Matter Expert, advising technical and security teams on AI-specific risks and appropriate controls
- Contribute to AI security standards, best practices, knowledge sharing, and the continuous development of internal security capabilities
