Group 07-75 | CO-OP | Systems Engineering | January to June 2026

Position Description

The Systems Engineering Group seeks a motivated AI/ML Intern to help implement a Retrieval-Augmented Generation (RAG) pipeline to enable natural language queries that return accurate and structured outputs.

The successful candidate should have at least a junior standing in their engineering field with coursework or projects in machine learning, databases, or natural language processing.

Responsibilities

• Work with the engineering team to understand database schema
• Implement data ingestion and embeddings into a vector store.
• Set up a RAG pipeline (e.g., using LangChain, LlamaIndex, or Haystack) connected to the SQL database.
• Develop simple prompts and queries to return structured data from natural language questions.
• Test the system with real engineering queries and improve retrieval accuracy.
• Document implementation steps and create a "how-to" guide for future engineers.

Qualifications

Required:

• 
  
  
  
  • Currently pursuing or recently completed a degree in Computer Science, Data Science, Electrical/Computer Engineering, or related field.
  • Familiarity with Python programming and working with APIs
  • Basic understanding of SQL databases (queries, joins, filtering).
  • Coursework or project exposure to machine learning or NLP.
  • Eagerness to learn and ability to work independently with guidance.
  
  
  
  

Preferred:

• Familiarity with vector databases
• Exposure to LLM frameworks (LangChain, LlamaIndex)
• Interest in electrical parts/cable assemblies (helpful but not required).

Key Skills

• Python programming
• SQL querying
• Basics of embeddings and retrieval-augmented generation (RAG)
• Documentation and communication

Internship Details

• Duration: 6 months
• Location: on-site
• Start date: Jan 2026