Responsibilities:

• Conduct comprehensive security assessments for internal and external generative AI systems
• Develop and execute security testing methodologies for Generative AI models
• Assist with setting up local language models using tools like ollama
• Identify and document potential vulnerabilities in Generative AI systems
• Analyze Generative AI model risks, including prompt injection, data leakage, and adversarial attacks
• Create detailed technical reports on Generative AI security findings and configuration guidelines
• Collaborate with internal AI development teams to implement security recommendations
• Research emerging AI security threats and mitigation strategies

Requirements:

• Degree in Cybersecurity, Computer Science or the equivalent with minimum 1 year of relevant experience in IT, cybersecurity and risk management
• Basic understanding of machine learning and AI principles
• Sound knowledge in Generative AI models
  o              GPT
  o              Llama
  o              Claude
  o              DeepSeek
  ·               Proficiency in:
  o              Python
  o              Cybersecurity tools
  o              Machine learning model analysis
  o              Vulnerability assessment techniques
  ·               Familiarity with:
  o              AI model testing frameworks
  o              Adversarial machine learning concepts
  o              Cloud security principles
  o              Running or setting up locally run models (ie ollama)
  o              Prompt engineering techniques