AI Security & Responsible AI Manager

Openkrill; United States; À distance; USD 83 000 - 185 000; Plein temps

Résumé du poste

Accenture Federal Services is seeking an AI security reviewer to validate compliance with internal AI security, Responsible AI, and data protection requirements across AI platforms and workflows. You will document non-compliance findings and mitigations while monitoring updates to AI models and frameworks.

You will also contribute to improving testing processes, creating reusable scripts, and updating security review criteria to maintain robust protection for government-facing AI systems.

Qualifications

• Strong understanding of GenAI ecosystems including LLMs, vector databases, prompt frameworks, agent orchestration, and multi agent workflows.
• Familiarity with AI security testing tools, red team prompt testing suites, agent behavior analyzers, and LLM evaluation frameworks.

Responsabilités

• Validate compliance with internal AI security, Responsible AI, and data protection requirements using established frameworks and checklists and output from AI testing tools.
• Document findings clearly, including non-compliance findings and recommended mitigations.
• Monitor updates to AI platforms, models, and frameworks to ensure test coverage remains current.
• Support continuous improvement by contributing to process and review enhancements, reusable scripts, and updated security review criteria.

Connaissances

GenAI ecosystems

AI security testing

RAI frameworks

Cloud security fundamentals

Python/JS scripting

Data protection

Technical writing

Outils

AI security testing tools

red team prompt testing suites

agent behavior analyzers

LLM evaluation frameworks

Description du poste

Accenture Federal Services is seeking an AI security reviewer to validate compliance with internal AI security, Responsible AI, and data protection requirements across AI platforms and workflows. You will document non-compliance findings and mitigations while monitoring updates to AI models and frameworks.

You will also contribute to improving testing processes, creating reusable scripts, and updating security review criteria to maintain robust protection for government-facing AI systems.