Description

Key Responsibilities

• Conduct security reviews of:
  • AI prompts
  • AI agents
  • Multi-agent workflows
  • Agentic automation tools
• Validate compliance with:
  • AI security standards
  • Responsible AI frameworks
  • Data protection requirements
• Document:
  • Security findings
  • Non-compliance issues
  • Recommended mitigations
• Monitor updates to:
  • AI platforms
  • Models
  • Frameworks
• Support continuous improvement by:
  • Enhancing review processes
  • Creating reusable scripts
  • Updating testing criteria

Required Skills

AI Security & GenAI Expertise

• Knowledge of AI attack vectors:
  • Prompt injection
  • Data leakage
  • Model inversion
  • Jailbreaking
  • Unsafe agent behavior
• Strong understanding of:
  • LLMs (Large Language Models)
  • Vector databases
  • Prompt frameworks
  • Agent orchestration
  • Multi-agent workflows

Security Testing & Tools

• Experience with:
  • AI security testing tools
  • Red-team prompt testing suites
  • Agent behavior analyzers
  • LLM evaluation frameworks

System Evaluation & Risk Analysis

• Ability to evaluate:
  • Hallucinations
  • Unauthorized data access
  • Harmful outputs
  • Misuse scenarios
• Ability to review:
  • Prompt configurations
  • Guardrails
  • System inputs
  • Testing outputs

Technical & Cloud Skills

• Understanding of cloud security:
  • Azure / AWS / GCP
• Basic scripting:
  • Python / JavaScript (for automation & testing)

Communication & Documentation

• Strong technical writing skills
• Ability to:
  • Document findings clearly
  • Communicate risks to engineers and leadership

Education

• Bachelor’s Degree required

Key Skills

Education

Bachelor's degree