AI Prompt Engineer

Description

The company is building AI solutions for U.S. Customs and Border Protection, applying generative AI to a mission that protects the nation's borders and supports lawful trade and travel.

You will join the company's Agile Solution Factory, a team that experiments quickly, learns continuously, and turns complex operational problems into AI tools that deliver measurable value to mission users.

Your work 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 critical information.

Responsibilities

• Design, refine, and iterate on prompts for generative AI models (LLMs) so they produce the behaviors, answers, and creative outputs needed.
• Test prompt variations side by side, analyze the results, and use them to keep improving.
• Debug unexpected model behavior by tracing root causes to the prompt structure, model limits, or data context.
• Work with several groups to build prompts into workflows that streamline manual processes.
• Contribute ideas and collaborate on strategies for model fine-tuning and Retrieval Augmented Generation (RAG) to raise accuracy.
• Track the latest advances in LLMs, generative AI, and prompt engineering methods.

Requirements

• You must be a U.S. citizen who can pass a CBP background investigation, which includes 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. These criteria are not limited to those listed.
• 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.
• 1+ years of software development experience, including internships or relevant academic project work.
• 1+ year of hands-on work with large language models (for example OpenAI GPT series, Llama, or Gemini) or other generative AI models.
• Experience with at least one programming language: Python or JavaScript/TypeScript.
• Familiarity with prompt engineering techniques, including few-shot, chain-of-thought, structured outputs, and function calling.
• Desired: problem-solving skills and a data-driven approach to experimentation and optimization.
• Desired: clear written and verbal communication, including explaining complex technical ideas.
• Desired: ability to work independently and with others in a fast-paced, 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 with up to 10% local travel.

No security clearance is required to start.

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

The proposed salary range is $50,500 - $101,000. Final pay depends on factors such as location, Federal Government contract labor categories and wage rates, relevant prior experience, specific skills, education, and certifications.

Benefits

• Competitive compensation.
• Flexible time off that lets you take the time you need.
• Access to learning resources, learning and development opportunities, and continuing education.
• Health, wellness, financial, retirement, and family support offerings.