AI Security Specialist

At Accenture Federal Services, nothing matters more than helping the US federal government make the nation stronger and safer and life better for people. Our 13,000+ people are united in a shared purpose to pursue the limitless potential of technology and ingenuity for clients across defense, national security, public safety, civilian, and military health organizations.

About the role

The AI Security Specialist will work within the Cyber Risk team in the Information Security organization. Join a technology company within global Accenture, recognized as a Glassdoor Top 100 Best Place to Work. We offer a collaborative and caring community where you feel like you belong and are empowered to grow, learn, and thrive through hands-on experience, certifications, industry training, and more.

Responsibilities

• Support the team by performing basic security reviews of AI prompts, skills, agents, and other related inputs, including reviewing prompt-based systems, simple agent workflows, and early-stage automation tools.
• Assist in checking compliance with internal AI security, Responsible AI, and data protection requirements using established frameworks, checklists, and outputs from AI testing tools.
• Document review results clearly, noting areas of concern and drafting initial mitigation suggestions for review by senior team members.
• Contribute to continuous improvement by updating team documentation, improving reusable scripts under guidance, and assisting in refining security review criteria.

Requirements

• Basic understanding of GenAI ecosystems, including LLMs, vector databases, prompt frameworks, and simple agent workflows.
• Awareness of common AI-specific attack vectors such as prompt injection, data leakage, model inversion, and unsafe agent actions.
• Familiarity with fundamental AI security testing tools and evaluation frameworks, with willingness to learn more advanced tools over time.
• Ability to identify basic AI system issues such as hallucinations, unauthorized access attempts, or harmful outputs.
• Understanding of core cloud security concepts across Azure/AWS/GCP, focused on identity, logging, and boundary protections.
• Ability to review AI prompt inputs, configuration settings, guardrails, and simple testing outputs with guidance from senior staff.
• Basic scripting ability (Python, JS, or similar) to help build or update small test cases and simple automation scripts.
• Ability to apply AI security and Responsible AI requirements using checklists, templates, and system documentation provided by senior team members.
• Solid communication and writing skills to document and share test results, findings, and recommended mitigations in a clear and structured format.
• Ability to communicate observed issues to engineers and product teams under the guidance of senior reviewers.
• Ability to explain basic AI security concerns in plain language.
• Ability to work independently and as part of a high-performing team.
• Commitment to continuously improve skills and stay current with changes in AI models, platforms, and emerging threats—tracking updates and integrating them into test coverage.
• Experience contributing to updates of AI security patterns, guidance, and internal testing frameworks.

Pay

The base pay range for this position in the states of California, Colorado, Hawaii, Illinois, Maine, Maryland, Massachusetts, Minnesota, New Jersey, New York, Vermont, Virginia, Washington, and the District of Columbia, and the city of Cleveland is $82,900—$184,500 USD. Compensation varies depending on factors including office location, role, skill set, and level of experience. Accenture Federal Services offers a wide variety of benefits.