Job Description

AI/ML Security Assessments & Risk Management

Conduct comprehensive security assessments of AI/ML systems, including data pipelines, model training environments, inference endpoints, and MLOps workflows. Identify complex risks related to

data privacy, data leakage, adversarial attacks, model poisoning, prompt injection, and misuse of AI technologies

. Evaluate threats across the AI lifecycle--from data collection to model retirement--and define appropriate mitigation actions.

AI Governance & Security Controls

Develop and implement

security controls, governance frameworks, and policies

for end-to-end AI lifecycle management. Support clients in complying with AI regulations, responsible AI principles, and data protection requirements (e.g., GDPR, NIST AI RMF).Create strategic roadmaps and executive-level recommendations for secure AI adoption.

Cloud & Infrastructure Security for AI

Design

secure cloud architectures

for AI workloads across AWS, Azure, and GCP.Implement best practices for

IAM, encryption, secrets management, container security, network segmentation, and secure data storage

. Assess and secure APIs, microservices, and application components that support AI models and intelligent systems.

Identity & Access Management for AI Agents

Design IAM models for AI agents, including

agent identities, delegated permissions, ephemeral credentials, and cross-system trust boundaries

. Implement

zero-trust principles

for agent authentication, authorization, and privilege controls.Develop patterns for

scoped access, JIT (Just-In-Time) authorizations, short-lived tokens, and decoupled privilege elevation

. Integrate IAM systems with AI agent orchestration and establish

access governance processes

, including permission reviews, certifications, and usage monitoring.

Client Communication & Advisory

Translate technical security risks into clear business impacts that executive stakeholders can act on.Prepare assessment reports, recommendations, threat models, and remediation plans for clients. Work cross-functionally with AI engineers, data scientists, IT security, and compliance teams to deliver secure AI solutions.

Required Skills & Qualifications

3-8+ years of experience in cybersecurity, cloud security, or data security roles. Demonstrated experience securing AI/ML platforms, models, pipelines, or agent-based systems.Strong knowledge of

cloud security

(AWS, Azure, GCP), IAM, network security, encryption, and API security. Understanding of

AI threats

such as adversarial ML, data contamination, and model theft.Experience with container platforms (Docker, Kubernetes) and MLOps tools (SageMaker, Vertex AI, Azure ML, MLflow). Excellent analytical and communication skills, with the ability to present findings to technical and non-technical audiences.

Preferred Qualifications

Certifications such as

CCSP, CISSP, CCIE, AWS/Azure/GCP Security Specialty

, or AI governance credentials. Experience in responsible AI, AI policy, or AI compliance frameworks. Background in security engineering, threat modeling, or red teaming for AI systems. * Experience working in consulting organizations or large enterprise security programs.