Lead AI Security Engineer

Role: Lead AI Security Engineer

We are seeking an experienced Lead AI Security Engineer to lead the secure design and implementation of AI-enabled applications and platforms. This role sits at the intersection of application security, AI/ML systems, and cloud security engineering, focusing on securing the full lifecycle of AI-driven solutions.

You will define secure architecture patterns, identify AI-specific threats, implement security controls, and support engineering teams in building secure, resilient, and responsible AI systems.

Key Responsibilities

1. AI Security Architecture & Design

• Design and validate secure architectures for AI/ML systems, including:
• LLM-based applications
• Retrieval-Augmented Generation (RAG) systems
• Agentic workflows
• Model APIs and inference services
• Define secure reference architectures and reusable patterns.
• Establish trust boundaries, identity controls, and secure data flows.
• Provide guidance on secure integration of AI frameworks and model platforms.

2. AI Threat Modeling & Risk Assessment

• Lead threat modeling for AI-enabled systems.
• Identify and assess risks such as:
• Prompt injection and jailbreak attacks
• Data poisoning and training data leakage
• Model inversion and extraction
• Unauthorized access and abuse of AI services
• Conduct security design reviews and provide actionable remediation guidance.
• Apply frameworks such as OWASP Top 10 for LLMs, NIST AI RMF, and MITRE ATLAS.

2. Cloud Security Engineering & Governance

• Define and implement cloud security strategies for AI/ML workloads across public cloud environments.
• Experience in managing CSPM tools such as Prisma, wiz, orca etc.
• Architect and oversee security controls for:
• IAM and least-privilege access
• Encryption and key management
• Network segmentation and zero-trust architectures
• Secrets management and workload isolation
• Secure APIs and service-to-service communication
• Logging, monitoring, and security telemetry
• Conduct cloud security architecture reviews, risk assessments, and control validations.
• Establish governance standards for secure cloud adoption, AI workloads, and platform security.

3. Guardrails & Security Controls

• Design and implement AI-specific controls, including:
• Prompt/input validation and filtering
• Output validation and sanitization
• Context isolation and data protection
• Access control for models, tools, and agents
• Implement safeguards such as:
• Human-in-the-loop approvals
• Scoped permissions for agent actions
• Content safety and abuse prevention mechanisms
• Validate control effectiveness against adversarial behavior.

4. Secure AI/ML Lifecycle (MLSecOps / DevSecOps)

• Integrate security into AI/ML pipelines, including:
• Data ingestion and preprocessing
• Model training, tuning, and deployment
• CI/CD and release workflows
• Implement automated security checks for:
• Models, datasets, and dependencies
• APIs and infrastructure
• Containers and IaC
• Establish secure practices for model versioning, promotion, and rollback.

5. Application Security & Platform Protection

• Apply secure-by-design principles to AI-enabled applications.
• Secure:
• APIs and service-to-service communication
• Authentication and authorization mechanisms
• Secrets management and data protection
• Protect AI data pipelines, embeddings, and vector stores.
• Ensure resilience against abuse and misuse of AI systems.

6. Software & AI Supply Chain Security

• Define and oversee secure software and AI supply chain practices.
• Drive enterprise adoption and governance of:
• SBOM (Software Bill of Materials)
• CBOM (Cryptography Bill of Materials)
• AIBOM (AI Bill of Materials)
• KBOM (Knowledge Bill of Materials)
• Establish processes for dependency tracking, model provenance, artifact integrity, and third-party AI risk management.
• Integrate BOM validation and supply chain controls into CI/CD and cloud-native deployment pipelines.
• Support vulnerability management, compliance, and software integrity initiatives.

Required Qualifications

• Bachelor's degree in Computer Science, Cybersecurity, or related field (or equivalent experience).
• 7+ years of experience in:
• Application security / product security / security architecture / Cloud security engineering
• 2+ years of experience in AI/ML or AI-enabled systems security.
• Strong knowledge of:
• Secure SDLC, threat modeling, and vulnerability management

API security, authentication/authorization, and secure design