AI Engineer (GenAI, RAG, Multi-Agent Systems)

About the role

CACI is seeking an AI Engineer to join its AI Center of Excellence within a fast-moving CTO organization that drives the integration and scaling of AI across CACI's mission, programs and business operations. This is a rapid, prototype-focused role: you will support different programs in 1-2 month rotational engagements, deploy working AI applications, establish best practices and transfer knowledge so teams become operationally independent. The work centers on GenAI technologies such as RAG pipelines, conversational AI platforms and multi-agent systems, using a solution catalog of battle-tested templates.

Key responsibilities

• Deliver production-ready AI solutions in 1-2 month rotations, including RAG pipelines, conversational platforms and multi-agent systems tailored to each program's mission and tech stack.
• Build and customize AI solutions with vector databases, orchestration frameworks and managed AI services, applying observability, security and cost controls.
• Integrate LLM APIs and AI services into existing workflows, apply responsible AI guardrails, configure monitoring and alerting, and resolve integration issues across cloud and on-premises environments.
• Lead hands-on training, create documentation and pair-program with teams so they can independently operate and evolve AI applications.
• Improve templates, create reusable patterns and document new techniques, then validate that teams reach full operational independence.
• Explore emerging GenAI tools, evaluate their fit for federal use cases and share insights through demos and documentation.

Required profile

• 3-5 years building production applications with Python/JavaScript, Git workflows and modern development practices.
• Practical experience with LLM-powered apps, agent patterns, RAG, prompt engineering, vector databases and observability; hands-on experimentation preferred.
• Strong background designing, implementing and troubleshooting RESTful and event-driven integrations.
• Proven ability to deliver solutions quickly in unfamiliar environments with evolving requirements.
• Strong communication skills, ability to document clearly and teach complex AI concepts, and ability to make trade-offs under pressure.
• Ability to obtain and maintain a clearance up to Top Secret.

Required skills

• Experience with AWS/Azure/GCP, containerization, CI/CD, infrastructure-as-code concepts and secure API/key management.
• Understanding of basic ML concepts and how they apply to LLM systems.
• Experience with GitLab, Jira and iterative delivery.
• Desired: AWS Bedrock/GovCloud, Azure OpenAI, Kubernetes, Terraform, JS/TS/Python, React or FastAPI, and experience with agentic AI, guardrails, embeddings and structured outputs.

What we offer

• Proposed pay range of $82,100-$172,400, depending on location, contract category, experience, skills and education.
• Healthcare, wellness, financial, retirement, family support, continuing education and time-off benefits.
• A flexible time-off benefit and access to learning resources.