Job Title: AI Security Specialist
Role Overview
We are seeking an experienced AI Security Specialist to lead rapid security assessments of AI/ML deployments across diverse enterprise environments. This role focuses on identifying and mitigating risks unique to AI systems, including LLM-based applications, data pipelines, and AI-driven workflows.
You will work closely with engineering and leadership teams to evaluate AI security posture, define governance frameworks, and translate technical risks into clear business impact.
Key Responsibilities
AI Security & Risk Assessment
- Perform security assessments for AI systems, including:
- Prompt injection attacks
- Model poisoning risks
- Data leakage through AI endpoints
- Adversarial input vulnerabilities
- Evaluate LLM security posture and implement:
- Access control mechanisms
- Output validation frameworks
- Safe deployment practices
- Develop and deliver rapid risk assessment reports with actionable recommendations
AI Governance & Compliance
- Apply security frameworks such as:
- NIST AI Risk Management Framework (AI RMF)
- SOC 2 controls for AI environments
- Define governance models for:
- Model lifecycle management
- Data privacy and protection
- AI usage policies and guardrails
Cloud & Infrastructure Security
- Design and assess secure AI architectures in cloud environments (Azure preferred)
- Implement and review:
- Role-Based Access Control (RBAC)
- Identity & Access Management (IAM)
- Secrets management and network segmentation
- Ensure alignment with shared responsibility models in cloud deployments
Cross-Industry Security Advisory
- Adapt security assessments across industries such as:
- Healthcare
- Financial Services
- SaaS / Technology
- Manufacturing / Industrials
- Provide risk guidance tailored to varying compliance and operational environments
AI Risk Strategy & Business Alignment
- Define a clear point of view on AI-specific risks vs traditional cybersecurity
- Translate technical findings into business impact:
- Revenue risk
- Operational disruption
- Regulatory exposure
- Present findings to senior stakeholders including CTOs, CIOs, and executives
AI-Driven Development & Tooling
- Experience with AI-assisted SDLC practices:
- Code generation and review (e.g., GitHub Copilot, Cursor, Claude)
- AI-driven testing and documentation
- Automated security scanning
- Strong expertise in prompt engineering, including:
- Structured prompting techniques
- Prompt versioning and evaluation
- Understanding of AI platforms:
- Azure AI Services
- AWS Bedrock
- Google Vertex AI
Required Qualifications
- 10+ years of experience in cybersecurity
- Minimum 3+ years focused on AI/ML security
- Proven experience conducting security assessments and risk analysis
- Strong knowledge of cloud security (Azure preferred)
- Experience working across multiple industries with varying compliance requirements
- Excellent communication skills with ability to engage executive stakeholders
Preferred Qualifications
- Published frameworks, whitepapers, or case studies on AI security
- Experience in AI red-teaming or adversarial ML
- Strong understanding of emerging AI threats and governance trends
- Hands-on exposure to enterprise AI implementations
Key Traits for Success
- Ability to perform fast-paced, high-impact assessments
- Strong analytical and problem-solving mindset
- Adaptability across different business environments
- Focus on business-driven security outcomes, not just technical findings
Nice to Have
- Active involvement in AI security or research communities
- Experience designing human-AI workflows with governance and oversight
- Perspective on AI automation opportunities across business functions
- Practical, hands-on usage of AI tools in daily workflows
Never miss an opportunity! Create an alert based on the job you applied for.
