IBM - Yorktown Heights, NY
posted 2 months ago
Full-time - Intern
Yorktown Heights, NY
Computer and Electronic Product Manufacturing
About the position
The Foundation Models for Data Software Engineer Intern position is a summer internship for 2025, aimed at students pursuing graduate studies in computer science and related fields. The role focuses on enhancing the capabilities of foundation models for various data management tasks, including data discovery, metadata enrichment, and automated data-driven insights. Interns will work on implementing interactive data workflows and agentic solutions, contributing to innovative projects in the field of data management.
Responsibilities
- Implement pipelines using foundational models for code generation specific to data tasks such as SQL for data retrieval.
- Develop novel autonomous agentic systems to compete with Text-to-SQL on public leaderboards like BIRD and Spider 2.0.
- Utilize techniques combining foundational models, knowledge graphs, and multi-modal data to improve data discovery and automated text-to-SQL tasks.
- Create generative AI tooling for DataOps, focusing on data integration and flows.
Requirements
- PhD or MS students pursuing graduate studies in computer science or related fields.
- Strong programming skills in Python.
Nice-to-haves
- Familiarity and working expertise with large language models (LLMs).
- Familiarity with knowledge graphs, RAG, and agentic frameworks.
- Familiarity with SQL, Langgraph, and Langchain.
