AI Security Architect

We are seeking an experienced and highly skilled AI Security Architect to join AI Security team in Israel. This is a hands-on, highly technical role responsible for defining security architecture and implementing robust security controls for our AI/ML systems and their underlying platforms.

You will serve as the team’s technical mentor and architecture authority, driving secure-by-design patterns across the AI/ML lifecycle (data, training, evaluation, deployment, and production monitoring) and proactively mitigating AI-specific threats such as model integrity risks, data poisoning, adversarial attacks, prompt injection, model extraction, and inference-time abuse. While you won’t manage people, you will lead technically, set standards, and guide engineers day-to-day through architecture, reviews, and delivery.

Key Responsibilities:

Architecture & Secure-by-Design Leadership

• Define and maintain AI security reference architectures for multiple AI deployment patterns, including MCP / Agentic AI and LLM application stacks (RAG, tools/plugins, agents, orchestration).
• Establish and evolve security requirements, patterns, and guardrails across the AI/ML SDLC (design → build → run), including secure pipelines and platform controls.
• Own AI security architecture decisions across critical domains: identity, secrets, data protection, network controls, tenancy boundaries, logging/telemetry, and isolation for training/inference.

Control Design & Implementation (Hands-on)

• Design and deploy controls to ensure model integrity and governance, including RBAC/ABAC for models, feature stores, data sets, registries, and evaluation artifacts.
• Build/enable technical mechanisms for provenance, attestation, signing, and approval workflows (where applicable) across datasets, models, prompts, and deployments.
• Drive implementation of runtime protections for AI services (abuse prevention, rate limiting, input/output validation, prompt-injection mitigations, model endpoint hardening, and monitoring).

Threat Modeling, Assurance, and Risk Reduction

• Conduct and lead AI/ML-specific threat modeling (data poisoning, model evasion, extraction, inversion, supply-chain, prompt attacks), translate findings into actionable backlogs, and drive remediation.
• Define and run security design reviews for AI initiatives; provide clear, pragmatic architecture guidance and document exceptions with risk acceptance paths.
• Establish AI security testing approaches (adversarial testing, red-teaming enablement, evaluation security, misuse/abuse cases) and integrate into delivery pipelines.

Tooling, Automation, and Operational Enablement

• Design and deliver AI security tooling to improve and automate cybersecurity posture (e.g., controls coverage, policy-as-code, detection engineering, vulnerability management integration, incident response playbooks for AI-specific events).
• Define logging/monitoring standards and detection use-cases for AI platforms and LLM apps (drift signals, anomalous access, suspicious prompt patterns, exfiltration indicators, policy violations).

Technical Mentorship & Influence (No Line Management)

• Act as the team’s technical mentor: coach engineers through designs, implementations, and trade-offs; raise engineering quality via reviews, pairing, and knowledge sharing.
• Lead by influence across Data Science, Engineering, Product, Platform, and Cybersecurity—driving alignment without formal authority.
• Create internal enablement materials: runbooks, architecture standards, reusable patterns, and reference implementations.

Requirements

Required Qualifications

Experience

• 6+ years in Information Security, Cloud Security, or Application Security.
• 2+ years securing AI/ML systems or LLM applications in production (or equivalent depth in architecture and threat modeling for AI-enabled systems).
• Proven track record designing security architectures and driving adoption across multiple teams.

Technical Expertise

• Deep understanding of the ML/AI lifecycle and associated security risks (training/inference threats, data governance, evaluation integrity, model/prompt supply chain).
• Strong expertise in cloud security (AWS/Azure/GCP) and AI/ML services (e.g., SageMaker, Vertex AI, Azure ML) plus container platforms/orchestration.
• Strong knowledge of data security (classification, encryption, masking/tokenization, key management, lineage/provenance).
• Strong knowledge of application security architecture and secure design patterns (API security, authz/authn, secrets, CI/CD, policy-as-code).
• Deep understanding of AI-specific threats/defenses: adversarial ML, data poisoning, prompt injection, model inversion, model extraction, inference-time attacks.
• Strong coding ability in Python and/or Go (building security tooling, automation, integrations, prototypes).

Soft Skills

• Excellent communication—able to translate complex AI security risks into clear engineering requirements and decision-ready trade-offs.
• Strong stakeholder management and ability to drive alignment and delivery across diverse teams.
• Practical, proactive mindset with strong problem-solving in ambiguous, fast-moving AI environments.

Preferred Qualifications

• BA/BS degree required; advanced degree (MS/PhD) in Computer Science, Data Science, Cybersecurity, or related field is a plus.
• Certifications such as CISSP, CSSLP, and/or relevant cloud/security certifications; AI security-focused training is a plus.
• Familiarity with AI security frameworks/standards and enterprise governance expectations.

We at Deloitte believe that diversity and inclusion among our people is a critical component of our success and that is why we cultivate an organizational culture that contains and embraces diversity in all its forms.

Description Hebrew

Requirements Hebrew