Data Analytics Engineer Intern

Requisition Number: 74974

The company built on breakthroughs. ​  
Join us.​    

Corning is one of the world’s leading innovators in glass, ceramic, and materials science. From the depths of the ocean to the farthest reaches of space, our technologies push the boundaries of what’s possible.  ​  

How do we do this? With our people. They break through limitations and expectations – not once in a career, but every day. They help move our company, and the world, forward. ​  

​At Corning, there are endless possibilities for making an impact. You can help connect the unconnected, drive the future of automobiles, transform at-home entertainment, and ensure the delivery of lifesaving medicines. And so much more.​   

Come break through with us.  

Corning's Manufacturing, Technology and Engineering division (MTE) is recognized as the leader in engineering excellence & innovative manufacturing technologies by providing diverse skills to Corning’s existing & emerging businesses.

We anticipate & provide timely, valued, leading edge manufacturing technologies and engineering expertise.  We partner with Corning’s businesses and the Science & Technology division. Together we create and sustain Corning’s manufacturing as a differential advantage.

Day to Day Responsibilities:

• Participate in developing AI Agent prototypes for internal scenarios; implement basic agent workflows (prompting, tool/function calling, memory/state) under guidance.
• Build and optimize RAG pipelines: data ingestion/cleaning, chunking strategy, embeddings, indexing, retrieval, re-ranking, and grounding/citation.
• Explore GraphRAG/knowledge-graph-assisted retrieval: help with schema design, entity/relation extraction, graph storage/query, and hybrid retrieval experiments.
• Assist in building evaluation datasets and metrics for RAG/Agent quality (e.g., Recall@k, MRR, answer correctness/groundedness), and iterate based on findings.

Requirement:

• Work with engineers to integrate components into services (e.g., simple APIs/scripts), write documentation, and present weekly progress updates.
• Continuously improve retrieval and generation quality through controlled experiments (prompting, query rewriting, retrieval parameters) and summarize learnings into best practices.
• Communicate effectively with cross-functional stakeholders; demonstrate independent thinking, proactive problem solving, and a positive, open personality.
• Currently pursuing a Master’s degree (enrolled) in Computer Science, Artificial Intelligence, Data Science, Software Engineering, or a related major.
• Familiar with AI Agent frameworks and RAG/GraphRAG concepts; candidates with hands-on project experience (course/research/industry/open-source) are preferred.
• Internship availability: 4+ days/week; 3+ months is preferred.
• Proficient in Python; able to write readable, testable code with basic engineering practices (logging, error handling, version control).
• Good understanding of RAG: document processing, chunking, embedding, indexing, retrieval & re-ranking, grounding/citation; end-to-end project experience is a plus.
• Familiar with mainstream AI Agent frameworks (e.g., LangChain / LlamaIndex / Semantic Kernel or similar) and agent design patterns (planning/orchestration, tools, memory/state).
• Understand knowledge graph fundamentals and GraphRAG approaches; experience with graph databases/query (e.g., Neo4j/Cypher or similar) is a plus.
• Able to design basic experiments and evaluations for retrieval/generation quality (e.g., Recall@k, MRR, groundedness), analyze results, and iterate systematically.
• Independent thinker with strong communication skills; proactive, open-minded, and positive personality; able to collaborate and ask good questions.