AI Platform Engineering Intern (Undergraduate)

Ellucian•Reston, VA

About The Position

At Ellucian, an internship is more than just checking a box — it’s about learning by doing. Our award-winning internship program gives interns the opportunity to build real skills through hands-on experience, working alongside their teams on meaningful projects that support colleges and universities and ultimately impact students just like you. Throughout the program, you’ll contribute to meaningful projects, gain exposure to how teams collaborate, and explore your interests as you begin shaping what’s next in your career. You’ll be supported by your manager, dedicated project guides, and a structured mentorship program, as well as a broader intern community designed to help you learn and grow. Additionally, you will participate in executive Q&A sessions and “day-in-the-life” conversations with intern alumni & leaders across our organization, offering insights into career paths at Ellucian — many of which began through this very program. Our full-time internship program will run from May 18, 2026 – August 7, 2026. Apply Now to experience what it’s like to live the #ellucianlife. Project Overview Ellucian is seeking three driven and technically strong AI Platform Engineering Interns to join our AI Platform team in Reston, VA for Summer 2026. This is not a shadowing internship. You will be a working engineer on the AI Platform team, shipping production code against a real roadmap. Every engineering team today is adopting AI — your job is to build the layer underneath: the infrastructure that governs, measures, and scales AI as an engineering resource across the organization. You’ll write JavaScript, Node.js, and Python, deploy to AWS, integrate LLM APIs, and work with vector databases. You will operate in an agentic development workflow — directing AI agents that handle code generation, testing, and documentation while you remain accountable for correctness and quality. This is how engineering works here: the human shifts from writing every line to directing and governing the resources that do.

Requirements

Currently pursuing a BS or MS in Computer Science, Software Engineering, or a related field (rising junior, senior, or graduate student preferred).
Strong programming skills in JavaScript, Node.js, and Python, demonstrated through coursework, personal projects, or open-source contributions.
Solid understanding of data structures, algorithms, and systems design. You should be comfortable reading and writing code, not just completing exercises.
Hands-on experience directing AI agents as part of how you get work done — not just chatting with them, but managing their output and owning the result.
Familiarity with Git, REST APIs, and at least basic exposure to cloud services (AWS preferred).
Strong documentation skills.
Intellectual curiosity about how LLMs work, how AI agents are built, and the unsolved problem of governing and managing AI at the organizational level — not just how individuals adopt AI, but how engineering teams plan, measure, and coordinate it as a resource.

Nice To Haves

Experience with AWS services (Lambda, API Gateway, ECS, DynamoDB, S3, CloudWatch, etc.)
Experience with TypeScript
Experience building agentic workflows (tool calling, multi-step reasoning flows, retrieval/RAG patterns)
Exposure to LangChain and/or LangGraph
Awareness of multi-agent orchestration patterns
Familiarity with testing frameworks, CI/CD pipelines, or serverless architectures
Projects or coursework that go beyond individual AI adoption — thinking about how AI changes team workflows, cost structures, or engineering management

Responsibilities

Build Production Features: Develop and ship features on a Node.js serverless application running on AWS — against a real product backlog with tracked stories. The stack is evolving, and you’ll have a voice in those decisions.
LLM Infrastructure: Engineer the infrastructure layer between the organization and LLM providers — routing, streaming, cost tracking, and rate limiting.
Build Enterprise Integrations: Develop governed integrations between AI agents and enterprise systems — project trackers, source control, knowledge bases, and IT service management — with authentication, policy enforcement, and data access controls.
Observability and Cost Attribution: Build observability tooling that tracks AI usage and spend — creating dashboards and reporting that tie AI investment to business outcomes.
Enterprise Knowledge Systems: Build knowledge systems that give AI agents the organizational context required to operate effectively — including document ingestion pipelines and retrieval-augmented generation (RAG) patterns.
Collaborate with Engineering Teams: Work alongside engineering teams across Ellucian who are your platform’s users — understand how they work with AI in their workflows and build the infrastructure that governs and scales it.
Ship to Production: Participate in the full SDLC — Agile sprint ceremonies, pull request reviews, CI/CD pipelines, and production deployments — on infrastructure that engineering teams across Ellucian depend on.