AI Prompt Engineer
About the role
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
CACI is currently looking for a AI Prompt Engineer to join our BEAGLE (Border Enforcement Applications for Government Leading-Edge Information Technology) Agile Solution Factory (ASF) Team supporting Customs and Border Control (CBP) client located in Northern Virginia! Join this passionate team of industry-leading individuals supporting the best practices in Agile Software Development for the Department of Homeland Security (DHS). As a member of the BEAGLE ASF Team, you will support the men and women charged with safeguarding the American people and enhancing the Nation's safety, security, and prosperity. CBP agents and officers are on the front lines, every day, protecting our national security by combining customs, immigration, border security, and agricultural protection into one coordinated and supportive activity. ASF programs thrive in a culture of innovation and are constantly seeking individuals who can bring creative ideas to solve complex problems, both technical and procedural at the team and portfolio levels.
The Opportunity
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
- Bachelor's degree in Computer Science, Software Engineering, Information Technology, or related field (equivalent experience may be considered in lieu of degree).
- 0-3 years of professional software development experience, internships, or relevant academic project work.
- 1+ year of hands-on experience working with Large Language Models (e.g., OpenAI GPT series, Llama, Gemini) or other generative AI models.
- Experience with at least one programming language (Python, JavaScript/TypeScript)
- Familiarity with prompt engineering techniques (few-shot, chain-of-thought, structured outputs, function calling)
Desired:
- Problem-solving skills, with a data-driven approach to experimentation and optimization.
- Witten 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.
- 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
-
What You Can Expect:
A culture of integrity.
An environment of trust.
A focus on continuous growth.
Not included in the source posting: about the role, benefits.
Skills
Who can apply
The employer didn't state any visa, work authorization, citizenship or clearance requirements in this posting. Confirm with the employer before applying.
Read automatically from the employer's posting text. Always confirm with the employer — requirements can change after a job is published.