Job Title: Senior GenAI Engineer Job Category: Information Technology Time Type: Full time Minimum Clearance Required to Start: Secret Employee Type: Regular Percentage of Travel Required: Up to 10% Type of Travel: Local * * * The Opportunity: Join our team as a Senior GenAI Engineer supporting Department of War PPBE (Planning, Programming, Budgeting, and Execution) applications. You'll build cutting-edge AI solutions that directly modernize how the DoW plans, programs, budgets, and executes critical defense operations. You’ll work with cross-functional teams to develop AI-enabled features, build intelligent document processing pipelines, and deliver data-driven analytics for mission-critical defense financial systems. While the bulk of this role focuses on generative AI, you will also apply traditional machine learning techniques for forecasting, anomaly detection, and trend analysis on budget and execution data. This role operates across both unclassified and classified environments. Responsibilities: - Design and develop AI-enabled features for PPBE applications using LLMs, GenAI, and agentic AI patterns - Build RAG pipelines over budget justification documents, appropriation language, execution data, and DoD directives - Implement agentic workflows using orchestration frameworks (LangGraph, Agno, Haystack, CrewAI) for multi-step budgeting tasks such as POM construction, BES preparation, and J-Book generation - Develop traditional ML models for budget execution forecasting, obligation rate anomaly detection, and spend trend analysis - Implement prompt engineering strategies and integrate AI/LLM APIs (OpenAI, Anthropic, Bedrock) - Architect full-stack AI features with reliable API integrations, error handling, and graceful degradation - Establish LLM observability (cost, latency, quality) and responsible AI guardrails (hallucination detection, output validation, CUI safeguards) - Maintain full-stack applications (including Web Application development using modern technologies such as React, TypeScript, NodeJS, Python, and .NET) - Address security vulnerabilities and ensure compliance with DoD cybersecurity standards - Participate in code reviews, CI/CD pipelines, and collaborative development workflows - Document technical implementations and stay current with AI and ML developments Qualifications: Required: - Active Secret clearance - Bachelor’s degree in Computer Science, Data Science, Mathematics, or related STEM field. Masters degree preferred. - Masters degree and 12+ years of SDLC experience OR Bachelors and 15+ years of SDLC experience - Security+ Certification - 2+ years experience developing generative AI / LLM-powered applications - Expert-level proficiency in Python; strong JavaScript proficiency - Experience with RESTful APIs and integrating AI/LLM APIs (OpenAI, Anthropic, Bedrock) - Experience with prompt engineering techniques (few-shot, chain-of-thought, system prompts) - Experience with LLM orchestration frameworks such as LangGraph, Agno, CrewAI, or similar - Experience with RAG architectures, agentic patterns, and vector databases - Strong understanding of ML fundamentals (supervised/unsupervised learning, model evaluation, feature engineering, NLP) - Experience with data analysis and ML libraries (pandas, NumPy, scikit-learn, or equivalent) - Experience with containerization (Docker) and at least one major cloud platform (AWS, Azure, or GCP) - Proficiency with Git version control and CI/CD pipelines - Strong written and verbal communication skills Desired: - Experience building predictive models for financial forecasting, anomaly detection, or resource allocation optimization - Experience with vector databases (Chroma, Weaviate, pgvector) and embedding models - Familiarity with LLM observability tools (LangFuse, LangSmith, Weights & Biases) - Understanding of responsible AI concepts: bias mitigation, hallucination detection, safety guardrails - Experience with AWS GovCloud, AWS Bedrock, or Azure OpenAI Service - Working knowledge of Kubernetes, Terraform or other IaC tools, and infrastructure automation - What You Can Expect: A culture of integrity. At CACI, we place character and innovation at the center of everything we do. As a valued team member, you’ll be part of a high-performing group dedicated to our customer’s missions and driven by a higher purpose – to ensure the safety of our nation. An environment of trust. CACI values the unique contributions that every employee brings to our company and our customers - every day. You’ll have the autonomy to take the time you need through a unique flexible time off benefit and have access to robust learning resources to make your ambitions a reality. A focus on continuous growth. Together, we will advance our nation's most critical missions, build on our lengthy track record of business success, and find opportunities to break new ground — in your career and in our legacy. Pay Range: There are a host of factors that can influence final salary including, but not limited to, geographic location, Federal Government contract labor categories and contract wage rates, relevant prior work experience, specific skills and competencies, education, and certifications. Our employees value the flexibility at CACI that allows them to balance quality work and their personal lives. We offer competitive compensation, benefits and learning and development opportunities. Our broad and competitive mix of benefits options is designed to support and protect employees and their families. At CACI, you will receive comprehensive benefits such as; healthcare, wellness, financial, retirement, family support, continuing education, and time off benefits. Since this position can be worked in more than one location, the range shown is the national average for the position. The proposed salary range for this position is: $105,100-$231,100 CACI is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, pregnancy, sexual orientation, age, national origin, disability, status as a protected veteran, or any other protected characteristic.

• Operationalize GenAI and LLM applications, leveraging RAG (retrieval-augmented generation), vector search, prompt engineering, agentic AI, and MCP (Model Context Protocol). • Lead the design, development, and deployment of production-grade LLM and ML pipelines, including data transformation, feature engineering, training, tuning, and serving. • Architect scalable data and AI workflows on Snowflake, Databricks, and Azure ML, integrating AI models with modern data lakehouse platforms. • Build and maintain API-based AI services (FastAPI, Flask), enabling secure, performant, and reliable model access at scale. • Define and implement CI/CD pipelines for GenAI and ML services, using GitHub Actions/Azure DevOps, MLFlow, and container orchestration (Kubernetes, Docker). • Develop and enforce MLOps/LLMOps best practices, including experiment tracking, model versioning, observability, and governance. • Mentor ML engineers and data scientists on engineering rigor, scalable design, and production-readiness. • Partner with cross-functional teams to integrate AI services into products, ensuring security, compliance, and resilience in regulated healthcare environments. • Troubleshoot production AI systems, analyzing inference latency, drift, and performance issues, and implementing preventive solutions. • Document and communicate architecture patterns, operational standards, and AI development frameworks across the organization.

• Define and deliver the roadmap to drive execution and scale of the AI Platform that supports internal stakeholders and external AI products. • Operate at the intersection of machine learning systems, data engineering, and applied healthcare AI. • Partner closely with AI engineers, data scientists, and clinical leadership to deliver production-grade systems that support reliable inference pipelines across millions of patient records. • Contribute to the improvement of quality and cost of care for over 2 million patients served by Aledade providers.

• Build and improve AI chatbot agents powered by LLMs, including retrieval-augmented generation (RAG), prompt engineering, and tool orchestration • Develop and refine fraud detection models using embeddings, semantic search, and rule-based systems • Design and maintain data pipelines, including ingestion, embedding, vector storage, and retrieval quality • Build evaluation frameworks to measure and improve AI agent accuracy and response quality • Collaborate with Engineering and Product teams to ship features end-to-end in a fast-paced, agile environment • Write clean, testable code and contribute to our AI platform and internal tooling • Gain exposure to technologies such as Python, FastAPI, LangChain, LangGraph, Google Gemini / Vertex AI, vector databases (pgvector, FAISS), AWS (EKS, S3), Docker, Kubernetes, Streamlit