AI Prompt Engineer at CACI in Washington, DC

Job description

Job Title: AI Prompt Engineer Job Category: Information Technology Time Type: Full time Minimum Clearance Required to Start: None Employee Type: Regular Percentage of Travel Required: Up to 10% Type of Travel: Local * * * The Opportunity: CACI is seeking a forward-thinking AI Prompt Engineer to join a team delivering innovative AI solutions in support of U.S. Customs and Border Protection (CBP). This is a unique opportunity to apply cutting-edge generative AI technologies to one of the nation's most critical missions. In this role, you will help modernize how frontline personnel access information, make decisions, and execute their work. By leveraging AI-powered tools and large language models, you will develop solutions that improve efficiency, enhance situational awareness, and accelerate access to mission-critical information. Your work will directly support the men and women responsible for protecting our nation's borders, facilitating lawful trade and travel, and safeguarding our nation. You will be part of CACI's Agile Solution Factory, a collaborative environment focused on rapid innovation, experimentation, and continuous learning. We are seeking individuals who combine creativity, technical curiosity, and a passion for exploring the evolving capabilities of AI. The ideal candidate can translate complex operational challenges into practical, high-impact AI solutions that deliver measurable value to mission users. Candidates will participate in a structured AI Prompt Engineering training program prior to transitioning to a client facing assignment. Responsibilities: Prompt Design & Optimization: Develop, refine, and iterate on prompts for various generative AI models (LLMs) to elicit desired behaviors, responses, and creative outputs. Iterative Testing & Analysis: Conduct testing to compare prompt variations, analyze results drive continuous improvement. Collaboration: Work closely with multiple groups to integrate prompts to streamline manual processes. Research & Development: Stay abreast of the latest advancements in LLMs, generative AI, and prompt engineering techniques. Fine-tuning & RAG Support: Provide input and collaborate on strategies for model fine-tuning and Retrieval Augmented Generation (RAG) to further improve accuracy. Problem Solving: Debug unexpected model behaviors, identifying root causes within prompt structure, model limitations, or data context. Qualifications: Required: Must be a U.S. Citizen with the ability to pass CBP background investigation, criteria include, but not limited to: 3-year check for felony convictions 1 year check for illegal drug use 1 year check for misconduct such as theft or fraud High School diploma or equivalent completed prior to start Must be available to work onsite in Ashburn, VA and/or Washington, D.C. Problem-solving skills, with a data-driven approach to experimentation and optimization. Written and verbal communication skills, with an ability to articulate complex technical concepts clearly. Ability to work independently and collaboratively in a fast-paced, evolving environment. Desired: Software development experience, internships, or relevant academic project work. Hands-on experience working with Large Language Models (e.g., OpenAI GPT series, Llama, Gemini) or other generative AI models. Experience with any programming language (Python, JavaScript/TypeScript, etc.) Familiarity with prompt engineering techniques (few-shot, chain-of-thought, structured outputs, function calling) Exposure to RAG concepts, including embeddings and vector databases Understanding of AI safety considerations (e.g., prompt injection, bias, data privacy) Exposure to Agile/Scrum development environments This position is contingent on funding and may not be filled immediately. However, this position is representative of positions within CACI that are consistently available. Individuals who apply may also be considered for other positions at CACI. What You Can Expect: A culture of integrit