AI Security Engineer, Vulcan at OneDegree

Vulcan is seeking an AI Security Engineer to address customer concerns regarding AI security, prompt engineering, and model integrity. The candidate will have hands-on development experience and expertise in defining and refining prompts generated by AI systems. This role involves working closely with clients to mitigate security risks and ensure AI safety.

Responsibilities:

• Design, refine, and optimize AI-generated prompts
• Develop techniques to prevent prompt-based security vulnerabilities
• Customize and integrate AI security solutions
• Implement security protocols for AI model deployment
• Conduct security assessments to identify vulnerabilities
• Collaborate with clients to understand their AI security concerns
• Stay updated on AI security trends and emerging threats

Requirements:

• Bachelor's, Master's, or Ph.D. in Computer Science, AI, Cybersecurity, or related field
• Strong programming expertise in Python
• Experience with ML frameworks such as PyTorch, TensorFlow
• Hands-on experience with prompt engineering, NLP, NLU, and LLM fine-tuning
• Knowledge of cybersecurity principles, risk assessment, and AI-specific security methodologies
• Excellent communication skills
• Ability to write and speak in English fluently

The role offers:

• Opportunity to work with interdisciplinary teams
• Chance to contribute to internal research and development efforts