Embedded System Engineer Intern Jobs in Berwyn, IL

The job responsibilities outlined in this document are not exhaustive and may evolve over time and be reviewed according to business needs.

ROLE DESCRIPTION

The SES Product and Innovation Engineering team is building the next generation of intelligent, AI-powered products — and we want interns excited to be at the frontier of that work. We’re looking for an AI Engineer Intern who can help architect and ship custom AI agents, Retrieval-Augmented Generation (RAG) pipelines, and full-stack AI applications grounded on our proprietary knowledge bases and custom APIs.

As an Java AI Engineer Intern, you’ll work alongside experienced engineers to design and build systems that connect LLMs to live data sources, internal APIs, and enterprise tooling. Utilizing Agile methodology, you’ll collaborate with engineers, product owners, and key stakeholders. The ideal candidate understands how to build reliable, production-ready AI systems — not just proof-of-concept demos.

PRIMARY RESPONSIBILITIES

Apply your understanding of large language models (LLMs) to design and build custom AI agents capable of reasoning, planning, and taking actions via tool use and API integrations.
•    Architect and implement RAG pipelines — including document ingestion, chunking strategies, embedding generation, vector storage, and semantic retrieval — grounded on internal knowledge bases and custom APIs.
•    Build full-stack AI applications with a Java/Python-based backend (FastAPI/Flask) and a functional frontend UI (React or Next.js) that surfaces agent outputs and conversational interfaces to end users.
•    Integrate LLM agents with custom REST APIs using function calling / tool use patterns so agents can take real actions against live systems.
•    Contribute to prompt engineering and context management strategies — including system prompts, few-shot examples, and context window optimization — to improve agent reliability and output quality.
•    Collaborate with engineers and product stakeholders to define agent behavior, memory patterns, and guardrails that align with business requirements.
•    Write clean, well-tested code, participate in code reviews, and document your implementations so the team can build on your work.
•    Participate actively in Agile ceremonies such as daily stand-ups, backlog refinement, sprint planning, and retrospectives.
•    Communicate effectively with team members and stakeholders to clarify requirements, share progress, and resolve technical challenges promptly.

COMPETENCIES

•    Deep understanding of LLM concepts including prompt engineering, embeddings, function calling, and RAG architecture.
•    Proficiency in Python for building AI pipelines, APIs, and data workflows.
•    Hands-on experience with LLM orchestration frameworks such as LangChain, LlamaIndex, or equivalent.
•    Ability to architect and implement end-to-end RAG pipelines including vector database integration (Pinecone, ChromaDB, AWS OpenSearch, or pgvector).
•    Strong REST API consumption skills — able to wire LLM agents to external data sources with minimal friction.
•    Familiarity with AWS services (S3, Lambda, Bedrock, OpenSearch) in a cloud-first environment.
•    Clear communication skills — able to explain AI behavior, trade-offs, and results to both technical and non-technical stakeholders.

QUALIFICATIONS & EXPERIENCE

•    Currently pursuing a Bachelor’s or Master’s degree in Computer Science, Data Science, Machine Learning, or a related field.
•    Strong foundation in Python — comfortable building and deploying scripts, APIs, and data pipelines.
•    Working knowledge of LLM concepts: prompt engineering, token limits, function/tool calling, embeddings, and chat completion APIs (OpenAI, Anthropic, or similar).
•    Exposure to at least one LLM orchestration framework such as LangChain, LlamaIndex, or equivalent.
•    Understanding of RAG architecture: chunking, embedding models, vector databases (e.g., Pinecone, ChromaDB, pgvector, or AWS OpenSearch), and retrieval strategies.
•    Familiarity with REST API design and consumption — comfortable reading API docs and wiring LLM agents to external data sources.
•    Basic experience with frontend development (React, Next.js, or similar) sufficient to build a usable chat or agent UI.
•    Comfort working with AWS services (S3, Lambda, Bedrock, or EC2) or willingness to learn quickly in an AWS-first environment.
•    Strong communication skills — able to explain AI behavior, trade-offs, and results clearly to both technical and non-technical stakeholders.

OTHER KEY REQUIREMENTS / COMMENTS

•    Hands-on experience building multi-step or multi-agent workflows using frameworks like CrewAI, AutoGen, or LangGraph.
•    Familiarity with AWS Bedrock or Amazon OpenSearch for hosting and querying AI workloads in a managed cloud environment.
•    Experience with fine-tuning or parameter-efficient training (LoRA, QLoRA) on open-source models via Hugging Face.
•    Exposure to streaming response patterns (Server-Sent Events, WebSockets) for real-time AI UX.
•    Knowledge of agent memory patterns — short-term context, long-term persistent memory, and episodic retrieval strategies.
•    Experience with OpenAI Assistants API or GPT Actions for building structured, API-connected GPT workflows.
•    Familiarity with evaluation and observability tools for LLM applications (e.g., LangSmith, Weights & Biases, Arize, or custom evals).
•    Familiarity with Java and Spring Boot — useful for understanding and consuming enterprise backend services or microservices that AI agents may need to interface with.
•    Exposure to Dynatrace or similar APM/observability platforms (Datadog, New Relic) — understanding how to interpret telemetry, traces, and performance metrics that an AI agent might query or act on.
•    Prior internship or project experience shipping an AI-powered product or tool (even a side project counts!).

div.content {background: #FFFFFF;}div.joqReqDescription { background: #FFF repeat-y!important;font-family:Arial, Helvetica, sans-serif!important;text-align:left; color:#000;width:700px!important; margin:0 auto!important; position:relative; -webkit-column-count: 1; /* Chrome, Safari, Opera */ -moz-column-count: 1; /* Firefox */ column-count: 1;padding-top:0px;padding-left: inherit;padding-bottom:50px;font-size:14px}div.joqReqDescription div.image-box { width: 700px;text-align: center;display: block;padding: 0 0 35px;}div.joqReqDescription p, div.joqReqDescription ul{ font-family:Arial, Helvetica, sans-serif!important;margin:0 15px;padding-bottom:12px;}div.joqReqDescription li{ padding-bottom:6px;}/*position: absolute;height: 389px;}div.joqReqDescription div.imagebox2 {text-align:center;}*/