AI Prompt Engineer

CACI International•Laredo, TX

4d•$50,500 - $101,000•Onsite

About The Position

CACI is seeking an AI Prompt Engineer to join a team delivering generative AI solutions in support of U.S. Customs and Border Protection (CBP). The role applies AI technologies and large language models to modernize how frontline personnel access information, make decisions, and perform their work. The solutions are intended to improve efficiency, enhance situational awareness, and accelerate access to mission-critical information. The position is part of CACI's Agile Solution Factory, a collaborative environment focused on rapid innovation, experimentation, and continuous learning. The AI Prompt Engineer translates operational challenges into practical AI solutions and develops, tests, and improves prompts for generative AI models. The role also collaborates on model fine-tuning and Retrieval Augmented Generation strategies, works with other groups to integrate prompts into workflows, and investigates unexpected model behavior. The position requires onsite availability in Ashburn, Virginia and/or Washington, D.C. Travel of up to 10% may be required. Applicants must be U.S. citizens and able to pass a CBP background investigation.

Requirements

Must be a U.S. citizen and able to pass the CBP background investigation, including checks covering felony convictions, illegal drug use, and misconduct such as theft or fraud.
Must be available to work onsite in Ashburn, Virginia and/or Washington, D.C.
Bachelor’s degree in Computer Science, Software Engineering, Information Technology, or a related field; equivalent experience may be considered in lieu of a degree.
At least 1 year of software development experience, internships, or relevant academic project work.
At least 1 year of hands-on experience with large language models, such as OpenAI GPT, Llama, or Gemini, or other generative AI models.
Experience with at least one programming language, such as Python or JavaScript/TypeScript.
Familiarity with prompt engineering techniques such as few-shot prompting, chain-of-thought, structured outputs, and function calling.

Nice To Haves

Problem-solving skills and a data-driven approach to experimentation and optimization.
Written and verbal communication skills, including the ability to clearly explain complex technical concepts.
Ability to work independently and collaboratively in a fast-paced, evolving environment.
Exposure to Retrieval Augmented Generation concepts, including embeddings and vector databases.
Understanding of AI safety considerations, such as prompt injection, bias, and data privacy.
Exposure to Agile/Scrum development environments.

Responsibilities

Develop, refine, and iterate on prompts for generative AI models to elicit desired behaviors, responses, and outputs.
Test prompt variations, analyze results, and use findings to drive continuous improvement.
Work with multiple groups to integrate prompts and streamline manual processes.
Stay current on advancements in large language models, generative AI, and prompt engineering techniques.
Provide input and collaborate on model fine-tuning and Retrieval Augmented Generation strategies to improve accuracy.
Debug unexpected model behaviors by identifying causes related to prompt structure, model limitations, or data context.