Location:

Toronto, Canada Level:

Intermediate to Senior CISSP Preferred, Not Required Role Overview iVedha is looking for an AI Security Specialist / Architect with a strong foundation in cybersecurity and an understanding of emerging AI and Generative AI security risks . The successful candidate will work with our architecture, engineering, cloud and AI teams to help ensure security is designed into enterprise AI solutions from the beginning. This role is suitable for an intermediate-to-senior security professional who understands traditional enterprise security and wants to work more deeply with AI, LLMs, RAG and Agentic AI. Key Responsibilities Support security architecture and reviews for AI and cloud solutions. Perform security assessments and threat modeling for AI-enabled applications. Help identify risks associated with LLMs, RAG, AI agents, APIs and enterprise data. Define appropriate security controls for AI applications and agentic workflows. Review identity, access and permissions used by AI agents and applications. Help secure AI integrations with enterprise applications, APIs and data sources. Support security for MCP/tool connectivity and agent-to-agent interactions. Implement and review AI guardrails, access controls and monitoring. Work with development and platform teams to incorporate security into DevSecOps and CI/CD processes. Support vulnerability assessments, security testing and remediation. Assist with security governance, documentation, audit and compliance requirements. Stay current with emerging AI threats, vulnerabilities and security practices. Requirements AI Security Areas The candidate should have knowledge of, or a strong interest in developing expertise around: Generative AI and LLM security Prompt injection and jailbreak attacks Sensitive-data leakage RAG and vector database security AI agent permissions and access control Agent identity and authentication API and tool security MCP security AI model access and protection AI guardrails AI monitoring and observability Private and sovereign AI environments Human approval controls for sensitive AI actions The candidate does not need to be an AI/ML scientist , but should understand how modern AI applications are built and where security risks can occur. Core Cybersecurity Skills Candidates should have experience in several of the following areas: Security architecture Cloud security Identity and Access Management (IAM) Zero Trust Application security API security Network security Data security Vulnerability management DevSecOps Container/Kubernetes security SIEM and security monitoring Incident response Experience with Azure, AWS and/or Google Cloud is beneficial. Frameworks & Governance Familiarity with some of the following is preferred: NIST Cybersecurity Framework NIST AI Risk Management Framework

ISO 27001 ISO/IEC 42001 OWASP

guidance for LLM and Generative AI security

MITRE ATT&CK / ATLAS SOC 2

Zero Trust principles Deep expertise across every framework is not required . Experience Typically 4-8+ years of cybersecurity experience , although strong candidates with relevant hands-on experience will also be considered. Experience with AI security is preferred, but candidates with a strong security background and demonstrated hands-on knowledge of Generative AI technologies are encouraged to apply. Preferred Qualifications CISSP preferred but not mandatory CCSP, CISM or equivalent security certifications are beneficial Cloud security certifications are beneficial Practical experience with AI/LLM security is highly valued Ideal Candidate We are looking for someone who can bridge the gap between: Cybersecurity

+ Cloud

+ Applications

+ Data

+ AI The candidate should be comfortable working with security architects, developers, cloud/platform engineers and AI engineers. They should be able to understand how an AI solution works, identify where the security risks are, and help the engineering team implement practical controls. Over time, this individual will have the opportunity to develop into a deeper AI Security Architect role as iVedha expands its AI-native and Agentic AI capabilities.

Pay:

From $75,000.00 per year

Work Location:

In person