Data Scientist - LLM & RAG for Industrial Utilities

3Core Systems, Inc; Indiana; On-site; USD 120,000 - 180,000; Full time

Job summary

3Core Systems, Inc. in Wayne, Indiana is seeking a data scientist with hands-on experience in large language models and retrieval-augmented generation to transform unstructured operational data into actionable insights.

The role focuses on designing RAG pipelines, fine-tuning LLMs, building vector databases, and deploying solutions in cloud environments (Azure/AWS). Collaboration with field Ops and engineering teams is essential.

Qualifications

• Experience in Data Science/Machine Learning with LLMs and Generative AI.
• Strong Python proficiency (PyTorch/TensorFlow) and SQL.
• Experience in utility/energy/industrial sectors.
• Knowledge of RAG and vector embeddings.

Responsibilities

• Develop RAG pipelines to enhance LLM-driven troubleshooting and field operations.
• Fine-tune and evaluate LLMs for task-specific reasoning and accuracy.
• Build high-quality Python code to integrate vector databases to store and retrieve documents efficiently.
• Apply LLM solutions to analyze unstructured utility data, such as asset management logs, SCADA alerts, and maintenance records.
• Deploy and scale models in cloud environments (Azure/AWS) with software engineers.
• Collaborate cross-functionally with field operations, engineering teams, and stakeholders to understand data needs and deliver solutions.

Skills

LLMs

RAG systems

Python

Vector embeddings

SQL

Tools

PyTorch

LangChain

LlamaIndex

Pinecone

Milvus

Job description

3Core Systems, Inc. in Wayne, Indiana is seeking a data scientist with hands-on experience in large language models and retrieval-augmented generation to transform unstructured operational data into actionable insights.

The role focuses on designing RAG pipelines, fine-tuning LLMs, building vector databases, and deploying solutions in cloud environments (Azure/AWS). Collaboration with field Ops and engineering teams is essential.