Federal AI Security Analyst - Risk & Compliance

Accenture Federal Services; Arlington (VA); On-site; USD 83,000 - 185,000; Full time

Job summary

Accenture Federal Services seeks an AI Security Specialist to support the Cyber Risk team in reviewing AI prompts, agent workflows, and related inputs. You will help ensure compliance with internal AI security and data protection standards and draft initial mitigation ideas for senior review.

You will contribute to updating documentation, refining security criteria, and building small automation scripts while staying current with AI model changes and emerging threats.

Qualifications

• Understanding of GenAI ecosystems and AI security concepts.
• Awareness of AI-specific attack vectors (prompt injection, data leakage, model inversion).
• Familiarity with AI security testing tools and evaluation frameworks.
• Ability to identify basic AI system issues (hallucinations, unauthorized access, harmful outputs).
• Understanding of Azure/AWS/GCP security basics (identity, logging, boundaries).
• Ability to review AI prompts, configurations, guardrails with guidance.
• Basic scripting ability (Python/JS) for test cases.
• Solid written communication to document findings and mitigations.
• Willingness to learn advanced tools and update testing patterns.

Responsibilities

• Support security reviews of AI prompts, skills, agents, and inputs.
• Check compliance with internal AI security and data protection frameworks.
• Document review results and draft mitigation suggestions for senior review.
• Contribute to process improvements and update security review criteria.

Skills

GenAI ecosystems

LLMs

vector databases

prompt frameworks

simple agent workflows

AI security testing tools

evaluation frameworks

identify AI issues

cloud security concepts

review prompts & guardrails

basic scripting

communication & documentation

Job description

Accenture Federal Services seeks an AI Security Specialist to support the Cyber Risk team in reviewing AI prompts, agent workflows, and related inputs. You will help ensure compliance with internal AI security and data protection standards and draft initial mitigation ideas for senior review.

You will contribute to updating documentation, refining security criteria, and building small automation scripts while staying current with AI model changes and emerging threats.