AI Prompt Engineer

Description

The company is hiring an AI Prompt Engineer for a full-time role supporting U.S. Customs and Border Protection (CBP). The work involves building AI solutions with generative AI and large language models to help frontline personnel find information, make decisions and carry out their work faster.

The role sits within the company's Agile Solution Factory, a team focused on quick experimentation and continuous learning. Before moving to a client-facing assignment, you will complete a structured AI prompt engineering training program. Travel is up to 10% and is local. No security clearance is required to start.

Responsibilities

• Write, refine and iterate on prompts for different generative AI models (LLMs) to get the behavior, responses and creative output you need.
• Test prompt variations, compare the results and use what you learn to keep improving them.
• Work with several teams to build prompts into processes that reduce manual work.
• Keep up with new developments in LLMs, generative AI and prompt engineering methods.
• Contribute ideas on fine-tuning and Retrieval Augmented Generation (RAG) strategies to raise accuracy.
• Find the cause of unexpected model behavior, whether it lies in the prompt structure, the model's limits or the data context, and fix it.

Requirements

• Strong problem-solving skills, with a data-driven approach to testing and optimization.
• Clear written and verbal communication, including explaining complex technical ideas simply.
• Ability to work alone and with others in a fast-moving, changing environment.
• High school diploma or equivalent, completed before your start date.
• Ability to pass a CBP background investigation. Checks include felony convictions (past 3 years), illegal drug use (past 1 year) and misconduct such as theft or fraud (past 1 year).
• U.S. citizenship is required.
• Preferred: software development experience, internships or relevant academic projects.
• Preferred: hands-on work with large language models such as the OpenAI GPT series, Llama or Gemini, or other generative AI models.
• Preferred: experience in any programming language, such as Python or JavaScript/TypeScript.
• Preferred: familiarity with prompt engineering techniques such as few-shot, chain-of-thought, structured outputs and function calling.
• Preferred: exposure to RAG concepts, including embeddings and vector databases.
• Preferred: understanding of AI safety issues such as prompt injection, bias and data privacy.
• Preferred: exposure to Agile or Scrum development.
• The role depends on funding and may not be filled right away. Applicants may also be considered for other open roles at the company.

Conditions

Full-time position based onsite in Ashburn, VA and/or Washington, D.C.

Travel is up to 10% and local.

Salary depends on factors such as location, federal contract labor categories and wage rates, prior experience, skills, education and certifications. The posted range is the national average, because the role can be filled in more than one location.

Proposed salary range: $39,400-$72,600.

Equal opportunity employer.

Benefits

• Comprehensive benefits including healthcare, wellness, financial, retirement, family support, continuing education and time off.
• A flexible time off benefit and access to learning resources.
• Learning and development opportunities.