Overview Sydney, NSW | Federal Government Program 12-Month Contract + Extension Options | Active Baseline Security Clearance Required Join a major Federal Government program building a greenfield AWS-based AI platform that will support innovative Generative AI solutions across the organisation. We are seeking an experienced AI Security Analyst to help secure the next generation of AI-enabled services within a cloud-native AWS environment. You will work alongside cloud engineers, platform specialists, security professionals, and AI practitioners to identify, assess, and reduce risks across AI systems, models, data, and infrastructure. The initial focus is supporting an AI-powered Case Assistant solution designed to ingest and analyse large volumes of documents, enable natural language querying, identify duplicate content, generate timelines, and improve staff productivity through intelligent automation. Responsibilities Protect AI systems, models, data, and infrastructure from attack, misuse, and unintended behaviour Identify AI security risks and recommend fit-for-purpose controls and mitigation strategies Conduct vulnerability assessments, break testing, security reviews, monitoring, and incident response activities Implement AI security controls including prompt security, input validation, response guardrails, and data protection measures Secure Retrieval-Augmented Generation (RAG) pipelines, including retrieval integrity, embedding security, vector database security, and prompt injection mitigation Assess and mitigate AI-specific threats including prompt injection, jailbreak attacks, document poisoning, and data leakage risks Monitor and support AI platforms using appropriate observability and security tooling Collaborate with engineering, cloud, platform, and governance teams to embed security throughout the AI development lifecycle Ensure compliance with government security requirements, Essential Eight, ISM, and relevant industry standards Contribute to security architecture, solution design documentation, and operational procedures Mentor and support team capability uplift in AI security practices Participate in Agile delivery activities and continuous improvement initiatives Qualifications Essential 2+ years' experience securing AI systems, models, prompts, and AI pipelines Hands-on experience conducting vulnerability assessments, break testing, monitoring, and incident response activities Experience implementing AI security controls including prompt security, response guardrails, data protection, and governance controls Strong understanding of AI/ML concepts, LLM security risks, and cloud-native architectures Experience performing security risk assessments and trust boundary analysis Strong knowledge of AWS security principles and cloud security best practices Understanding of ASD Essential Eight, ISM, ISO 27001, ISO 42001, or similar security frameworks Experience with DevSecOps, automation, and scripting tools Strong stakeholder engagement, communication, and documentation skills Relevant tertiary qualification in Computer Science, Information Technology, Cyber Security, or a related discipline Desirable Experience securing Generative AI platforms and production AI solutions Experience implementing security controls for LLM and RAG-based applications Experience with AWS Security Hub, GuardDuty, Inspector, IAM, and other AWS-native security services Experience securing OpenSearch, vector databases, S3, and RDS environments CISSP, AWS Security Specialty, or equivalent certifications Experience working in large-scale enterprise or government cloud environments Experience working within Agile delivery teams Why Join Work on a greenfield AWS AI platform delivering innovative Generative AI solutions Help shape the security foundations of enterprise AI capabilities Collaborate with highly skilled cloud, security, engineering, and AI specialists Exposure to emerging AI security challenges and technologies Long-term Federal Government contract with extension potential #J-18808-Ljbffr