Context Engineer

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.    Join Accenture Federal Services, 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.    Join us to drive positive, lasting change that moves missions and the government forward!  

You are:  

A Context Engineer, pivotal in orchestrating the delivery of AI-driven solutions - bridging business analysis, solution design, and integration to ensure AI has the right context to produce consistently strong, mission-aligned results. You translate approved user stories into AFS-compliant agent prompts, designs and governs the subagents that execute them, operates the AI build pipeline, and owns a high-performing prompt library. You integrate seamlessly with CI/CD pipelines while upholding security and ATO (Authority to Operate) compliance standards.

The work:

• Translate approved user stories into AFS-compliant agent prompts, ensuring alignment with project objectives and mission outcomes.
• Design the architecture for specialized subagents that operate within the build pipeline - defining each agent's purpose, scope, tools, and boundaries.
• Build routing, delegation, and escalation logic that determines when the system answers directly, invokes a subagent, runs specialists in parallel, asks a clarifying question, uses a tool, escalates to a human, or declines an unsafe action.
• Define agent-to-subagent contracts: inputs, context boundaries, structured outputs, confidence and evidence, latency budgets, cancellation behavior, and failure handling.
• Configure, manage, and operate AI build pipelines using generative agentic tools and orchestration frameworks (e.g., Claude, Codex, LangGraph).
• Own and maintain the prompt library including version control, quality scoring, and continuous improvement - refining prompts based on reviewed outputs and feedback.
• Create and maintain RAG knowledge bases and query prior context files for precedent and predictive insight before authoring new prompts.
• Oversee and integrate CI/CD pipelines, embedding security validations (SAST, vulnerability scanning) and automated ATO evidence generation for seamless compliance.