AI Prompt Engineer

Description

The company supports U.S. Customs and Border Protection (CBP) with AI solutions, and this role focuses on applying generative AI to a mission that protects the nation's borders and facilitates lawful trade and travel.

The work aims to change how frontline personnel find information, make decisions, and carry out tasks, using AI tools and large language models to improve efficiency, situational awareness, and access to critical information.

The role sits within the company's Agile Solution Factory, a team that experiments, iterates, and learns continuously. The ideal person turns complex operational problems into practical AI solutions that deliver measurable value to mission users.

Responsibilities

• Write, refine, and repeatedly revise prompts for generative AI models (LLMs) to produce the behaviors, answers, and creative outputs the team needs.
• Test prompt variations side by side, analyze the results, and use them to make ongoing improvements.
• Work with several groups to build prompts that simplify manual processes.
• Track current developments in LLMs, generative AI, and prompt engineering methods.
• Contribute ideas and work with others on fine-tuning and Retrieval Augmented Generation (RAG) approaches that raise model accuracy.
• Find the cause of unexpected model behavior, whether it lies in prompt structure, model limits, or the data context.

Requirements

• Required: U.S. citizenship and the ability to pass a CBP background investigation, which includes but is not limited to a 3-year check for felony convictions, a 1-year check for illegal drug use, and a 1-year check for misconduct such as theft or fraud.
• Required: Ability to work onsite in Ashburn, VA and/or Washington, D.C.
• Required: 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.
• Required: At least 1 year of software development experience, through work, internships, or relevant academic projects.
• Required: At least 1 year of hands-on experience with Large Language Models (such as OpenAI GPT series, Llama, or Gemini) or other generative AI models.
• Required: Experience in at least one programming language, such as Python or JavaScript/TypeScript.
• Required: Working knowledge of prompt engineering techniques such as few-shot prompting, 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 simply.
• Desired: Ability to work both independently and with others in a fast-moving, 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.

Up to 10% local travel.

Salary depends on factors such as location, Federal Government contract labor categories and wage rates, relevant experience, specific skills, education, and certifications.

The proposed salary range is $50,500 - $101,000.

The company offers flexibility to help employees balance quality work with their personal lives. Equal opportunity applies.

Benefits

• Flexible time off that lets you take the time you need.
• Access to learning resources for professional growth.
• Comprehensive benefits, including healthcare, wellness, financial, retirement, family support, continuing education, and time off.
• Competitive compensation and learning and development opportunities.