AI Prompt Engineer

Description

The company builds generative AI solutions for U.S. Customs and Border Protection (CBP) and is hiring an AI Prompt Engineer for a team doing that work.

You will help frontline personnel find information, make decisions and carry out tasks more efficiently, using AI tools and large language models to improve situational awareness and speed up access to information critical to missions. The work supports people who protect the borders, facilitate lawful trade and travel, and keep the country safe.

The role sits in the company's agile solution group, where teams experiment, ship quickly and keep learning. The ideal person turns complex operational problems into practical AI solutions that deliver measurable value to mission users.

Responsibilities

• Write and refine prompts for different generative AI models (LLMs) to get the behavior, answers and creative output you need.
• Test prompt variants side by side, study the results and use them to keep improving.
• Work with several groups to build prompts into workflows that cut manual work.
• Track new developments in LLMs, generative AI and prompt engineering methods.
• Give input on fine-tuning and Retrieval Augmented Generation (RAG) strategies to raise accuracy, and help shape them.
• Find the root cause of unexpected model behavior, whether it lies in prompt structure, model limits or data context, and fix it.

Requirements

• Hold U.S. citizenship and be able to pass a CBP background investigation. The checks include, but are not limited to, a 3-year review for felony convictions, a 1 year review for illegal drug use and a 1 year review for misconduct such as theft or fraud.
• Be able to work onsite in Ashburn, VA and/or Washington, D.C.
• Hold a bachelor's degree in Computer Science, Software Engineering, Information Technology or a related field. Equivalent experience may be considered in place of the degree.
• Have 1+ years of software development experience, internships or relevant academic project work.
• Have 1+ year of hands-on experience with Large Language Models (e.g., OpenAI GPT series, Llama, Gemini) or other generative AI models.
• Have experience with at least one programming language, such as Python or JavaScript/TypeScript.
• Know prompt engineering techniques such as few-shot, chain-of-thought, structured outputs and function calling.
• Desired: Strong problem-solving skills and a data-driven approach to testing and optimization.
• Desired: Clear written and verbal communication, including explaining complex technical ideas.
• Desired: Ability to work alone and in a team in a quickly changing environment.
• Desired: Exposure to RAG concepts, including embeddings and vector databases.
• Desired: Understanding of AI safety issues such as prompt injection, bias and data privacy.
• Desired: Exposure to Agile or Scrum development environments.

Conditions

Full-time, regular position.

No security clearance is required to start.

Travel of up to 10% of the time, local only.

Onsite work in Ashburn, VA and/or Washington, D.C.

Proposed salary range: $55,800 - $111,500.

Final pay depends on factors including location, Federal Government contract labor categories and wage rates, prior relevant experience, specific skills and competencies, education and certifications.

Benefits

• Comprehensive benefits covering healthcare, wellness, financial, retirement, family support, continuing education and time off.
• Flexible time off so you can take the time you need.
• Access to learning resources to help build your career.
• Competitive compensation and learning and development opportunities.