AI Engineer

CACI is seeking an AI Engineer to design, develop, test, and support AI-enabled applications and agent-based solutions for a United States Secret Service contract supporting the Department of Homeland Security. The role focuses on integrating AI models with enterprise data, applications, and workflows, including capabilities such as retrieval-augmented generation (RAG) and agent workflow development.

Location

Washington, DC (onsite)

Compensation

USD 120,800 - 265,800 per yearly

Role Summary

The AI Engineer will build and evaluate AI capabilities, integrating models with enterprise information sources and application workflows. Work includes developing RAG solutions, connecting AI systems to APIs and business processes, and establishing testing and evaluation routines for accuracy, relevance, grounding, safety, and performance. The position also supports deployment and operations activities such as CI/CD, monitoring, and incident resolution, while applying security and privacy requirements including identity and access controls.

Responsibilities

• Design, develop, test, document, and maintain AI-enabled applications and services.
• Implement AI and agent workflows using LangChain, Microsoft Agent Framework, or other suitable frameworks and services.
• Develop RAG capabilities, including data ingestion, retrieval, grounding, and integration with authorized enterprise information sources.
• Integrate AI models with APIs, enterprise applications, and business workflows, including appropriate tool use and human review.
• Partner with product owners, users, and functional specialists to translate needs into technical designs, user stories, and acceptance criteria.
• Develop and maintain application components, APIs, and services using Python and established software engineering practices.
• Create and execute automated tests and evaluations to assess accuracy, relevance, grounding, safety, and performance.
• Troubleshoot application and model behavior; improve solution quality using test results, telemetry, and user feedback.
• Support deployment and operations, including CI/CD, monitoring, documentation, incident resolution, and ongoing maintenance.
• Apply security and privacy requirements, including identity and access controls, authorization-aware retrieval, and protection of sensitive data.
• Collaborate with data, cloud, cybersecurity, DevSecOps, and software engineering teams to integrate solutions into the enterprise environment.
• Contribute reusable components, technical documentation, and engineering practices that improve consistency and maintainability.
• Support the development of AI Safety/Alignment policies and procedures for ethical, controllable, and aligned AI systems and agents.
• Support implementation of alignment controls in AI LLMs and agents by applying familiarity with AI safety frameworks such as the NIST AI Safety Framework.

Required Qualifications

• Bachelor's degree + 10 years of experience in artificial intelligence, machine learning, software engineering, or related field (equivalencies considered: Master's + 7 years; 16 years with no degree; AA + 12 years).
• At least five years of experience in software engineering, application development, AI/ML engineering, or a related technical field.
• Demonstrated experience developing software applications or services using Python and APIs.
• Hands-on experience building generative AI or machine learning applications that integrate models with data, applications, or workflows.
• Experience using LangChain, Microsoft Agent Framework, or a comparable framework to build AI or agent-based capabilities.
• Understanding of RAG, prompt and context design, model or application evaluation, and integration with enterprise data.
• Experience with automated testing, version control, and CI/CD practices.
• Familiarity with cloud-based application development and deployment; Microsoft Azure experience is preferred.
• Understanding of secure software development, including protecting sensitive information and restricting access to enterprise data.
• Ability to collaborate with technical teams, product staff, and functional stakeholders while communicating technical work clearly.

Preferred / Desired

• Experience developing production applications using both LangChain and Microsoft Agent Framework.
• Experience with LangGraph or other approaches for stateful, multi-step agent workflows.
• Experience with Azure OpenAI, Azure AI services, or Azure AI Foundry.
• Experience implementing authorization-aware RAG, data filtering, and access controls for retrieval and tool use.
• Experience with AI evaluation methods, test sets, tracing, observability, and monitoring for quality, latency, and cost.
• Experience integrating AI applications with enterprise systems, microservices, and web interfaces.
• Familiarity with responsible AI practices, including human review, explainability, and safe handling of uncertain or unsupported outputs.
• Relevant cloud, AI, or software engineering certifications.

Key Technologies

Python, LangChain, Microsoft Agent Framework, retrieval-augmented generation (RAG), NIST AI Safety Framework, CI/CD, Microsoft Azure

Travel Requirements

• Up to 10% travel
• Local travel

Benefits

• Healthcare
• Wellness
• Financial
• Retirement
• Family support
• Continuing education
• Time off benefits

What You Can Expect

• A culture of integrity
• An environment of trust
• Focus on continuous growth