Generative AI Engineering Intern Graduate - Peraton

Responsibilities

Peraton is seeking motivated Generative AI Engineering Interns (Graduate) supporting Internal Research and Development (IRAD) initiatives focused on AI/ML-driven platforms for Operations in the Information Environment (OIE). Interns can support 100% remotely.

This open-ended graduate internship is designed to provide sustained, meaningful work experience throughout your academic program. Interns will work 40 hours per week during the summer and 20 hours per week during the academic year, with the flexibility to increase to 40 hours per week as schedules allow. In this role, you will gain hands-on experience developing and applying cutting-edge generative AI solutions, including large language models (LLMs), prompt engineering, retrieval-augmented generation (RAG), and agentic AI architectures within a defense technology environment. Working alongside senior engineers and data scientists, you will support mission-critical information operations for Combatant Commands (COCOMs) by translating operational requirements into secure, production-grade AI solutions. The role offers exposure to enterprise software development practices such as Agile, DevSecOps, and CI/CD, as well as work with classified and sensitive data in FedRAMP-compliant cloud environments using technologies including Azure OpenAI Service, AWS, Python, LangChain, LlamaIndex, Hugging Face, vector databases, Docker, and Git. This internship provides competitive hourly compensation, flexible and remote-friendly scheduling, dedicated mentorship, networking opportunities across Peraton ’s technical leadership, and a potential pathway to full-time employment upon graduation.

Roles and responsibilities for this position include:

• Assist in the development and optimization of generative AI solutions using GPT-4, Claude, Gemini, and Azure OpenAI Service under the guidance of senior team members.
• Support prompt engineering efforts including designing, testing, and refining prompts to improve LLM output quality, accuracy, and consistency.
• Contribute to the implementation of retrieval-augmented generation (RAG) systems, including working with vector databases, embedding models, and semantic search pipelines.
• Conduct research on emerging generative AI techniques, foundation models, and best practices, summarizing findings for the development team.
• Assist in building evaluation frameworks and quality assurance pipelines to measure and improve AI-generated content quality.
• Support documentation efforts including creating technical guides, API documentation, and prompt libraries.
• Participate in code reviews, team meetings, and Agile/Scrum ceremonies to gain exposure to professional software development practices.
• Collaborate with cross-functional teams to understand operational requirements and translate them into technical solutions.
• Take on progressively complex responsib