Data Scientist

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

Job summary

3Core Systems, Inc. is seeking a data scientist to design and deploy LLM-based RAG systems for utility and industrial data. You will develop pipelines, fine-tune models, and integrate vector stores to turn unstructured logs into actionable insights.

Collaborating with field operations and engineering, you will deploy models in Azure/AWS and optimize for reliability and scalability in harsh industrial environments.

Qualifications

• 3+ years in Data Science/Machine Learning with focus on LLMs or Generative AI.
• Strong Python experience (PyTorch/TensorFlow) and familiarity with LangChain/LlamaIndex.
• Experience applying AI in utility, energy, or heavy-industrial sectors.
• Hands-on RAG expertise: embeddings, semantic search, and prompt engineering.

Responsibilities

• Develop RAG pipelines to improve LLM-driven troubleshooting and field ops.
• Fine-tune and evaluate LLMs for task-specific reasoning and accuracy.
• Build/optimize code to integrate vector databases for fast storage and retrieval of technical docs.
• Apply LLMs to analyze unstructured utility data like logs and maintenance records.
• Collaborate with field ops, engineering, and stakeholders to define data needs and deliver solutions.
• Deploy and scale models in Azure/AWS environments.

Skills

Data science

Machine learning

Generative AI

LLMs

Tools

Python

PyTorch

TensorFlow

LangChain

LlamaIndex

SQL

Pinecone

Milvus

Weaviate

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.