10285

3Core Systems; 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

Wayne, United States | Posted on 11/05/2026

We are seeking a highly skilled and motivatedData Scientist with a strong background in Large Language Models (LLMs) andRetrieval-Augmented Generation (RAG) systems.

The ideal candidate has direct experienceapplying AI within the utility, energy, or industrial sector.

You will lead the design, development, anddeployment of intelligent systems that translate unstructured operational data(technical manuals, maintenance logs, field reports) into actionable insights.

KeyResponsibilities:

• Develop RAG Pipelines: Design andoptimize Retrieval-Augmented Generation (RAG) models to enhance LLM-driventroubleshooting and field operations.
• AI Model Development: Fine-tune andevaluate LLMs (e.g., GPT-4, Llama 3) for task-specific reasoning and accuracy.
• Knowledge Integration: Build high-qualityPython code to integrate vector databases (e.g., Pinecone, Milvus, Weaviate) tostore and retrieve technical utility documents efficiently.
• Operational Intelligence: Apply LLMsolutions to analyze unstructured utility data, such as asset management logs,SCADA alerts, and maintenance records.
• Deployment: Work with software engineersto deploy and scale models in cloud environments (Azure/AWS).
• Collaboration: Work cross-functionallywith field operations, engineering teams, and stakeholders to understand dataneeds and deliver solutions.

RequiredQualifications:

• Experience: Professional experience inData Science/Machine Learning, with at least 1 year focusing specifically onLLMs and Generative AI.
• Technical Skills: Advanced proficiency inPython (PyTorch/TensorFlow, LangChain, LlamaIndex) and SQL.
• Domain Knowledge: Proven experience inthe utility, energy, oil & gas, or heavy industrial sectors.
• RAG Expertise: Hands-on experience withvector embeddings, semantic search, and prompt engineering.