Data Scientist

SIDRAM TECHNOLOGIES; Fort Wayne (IN); On-site; USD 150,000 - 190,000; Full time

Job summary

AEP in Fort Wayne, IN is seeking a highly skilled Data Scientist with a strong background in Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems.

The ideal candidate has direct experience applying AI within the utility, energy, or industrial sector and will lead the design, development, and deployment of intelligent systems that translate unstructured data into actionable insights.

Qualifications

• Proven experience applying LLMs and Generative AI in real projects.
• Strong Python skills with ML/NLP libraries and LangChain tooling.
• Experience integrating vector DBs and semantic search in production.

Responsibilities

• Design and optimize RAG pipelines to enhance LLM-driven troubleshooting.
• Fine-tune and evaluate LLMs (GPT-4, Llama 3) for domain tasks.
• Build and integrate vector databases to store utility documents.
• Apply LLMs to analyze unstructured operational data and logs.
• Collaborate with field ops, engineering, and stakeholders.
• Deploy and scale models in Azure/AWS cloud environments.

Skills

Python

PyTorch

TensorFlow

LangChain

LlamaIndex

SQL

LLMs

Generative AI

RAG

Prompt engineering

Tools

Pinecone

Milvus

Weaviate

Job description

Client: AEP
Location: 7775 Ardmore Ave, Fort Wayne, IN
Work Model: Onsite 5 Days a Week
Experience: 14+ Years
Employment Type: W2 Only
Visa: USC / H4EAD

Position Summary

We are seeking a highly skilled and motivated Data Scientist with a strong background in Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems. The ideal candidate has direct experience applying AI within the utility, energy, or industrial sector. You will lead the design, development, and deployment of intelligent systems that translate unstructured operational data (technical manuals, maintenance logs, field reports) into actionable insights.

Key Responsibilities

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

Required Qualifications

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

Submission Requirements

• 14+ Years of Professional Experience
• W2 Only
• USC / H4EAD Candidates Only
• Updated Resume
• Current Location
• Contact Details
• LinkedIn Profile