AI Security Specialist

Accenture Federal Services•Arlington, VA

17d•$82,900 - $184,500

About The Position

The AI Security Specialist will work within the Cyber Risk team in the Information Security organization. The role supports basic security reviews of AI prompts, skills, agents, and related inputs, including prompt-based systems, simple agent workflows, and early-stage automation tools. The specialist helps assess compliance with internal AI security, Responsible AI, and data protection requirements using established frameworks, checklists, and outputs from AI testing tools. The specialist documents review results, identifies areas of concern, and drafts initial mitigation suggestions for review by senior team members. The role also contributes to continuous improvement by updating team documentation, improving reusable scripts under guidance, and assisting with the refinement of security review criteria. The position requires a U.S. citizen and a bachelor's degree in a relevant field or equivalent experience, along with at least three years of relevant experience.

Requirements

U.S. citizen.
Bachelor's degree in Information Technology, Information Security, Business, or Risk Management, or equivalent experience.
At least 3 years of experience in Risk Management, Security Assessment, or a related field.
Basic understanding of GenAI ecosystems, including LLMs, vector databases, prompt frameworks, and simple agent workflows.
Awareness of 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, and willingness to learn more advanced tools.
Ability to identify basic AI system issues, including hallucinations, unauthorized access attempts, or harmful outputs.
Understanding of core cloud security concepts across Azure, AWS, or GCP, focused on identity, logging, and boundary protections.
Basic scripting ability in Python, JavaScript, or a similar language 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 clearly and in a structured format.
Ability to explain basic AI security concerns in plain language.
Ability to work independently and as part of a high-performing team.
Ability to continuously improve skills and stay current with changes in AI models, platforms, and emerging threats.

Nice To Haves

Experience contributing to updates of AI security patterns, guidance, and internal testing frameworks.

Responsibilities

Perform basic security reviews of AI prompts, skills, agents, and related inputs, including 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 AI testing tool outputs.
Document review results, identify concerns, and draft initial mitigation suggestions for senior team members to review.
Update team documentation and improve reusable scripts under guidance.
Assist in refining security review criteria and contribute to updates of AI security patterns, guidance, and internal testing frameworks.
Review AI prompt inputs, configuration settings, guardrails, and simple testing outputs with guidance from senior staff.
Communicate observed issues to engineers and product teams under the guidance of senior reviewers.
Track changes in AI models, platforms, and emerging threats and integrate relevant updates into test coverage.