Summary
Overview
Work History
Education
Skills
Websites
Certification
Languages
Timeline
Generic
Shubham Raj

Shubham Raj

Pune

Summary

Results-driven AI Engineer with expertise in AI, LLMOps, NLP, and Generative AI. Proven track record in developing innovative AI-driven solutions and optimizing models for production. Skilled in integrating LLM workflows to improve efficiency and productivity. Continuously updating knowledge to deliver cutting-edge solutions.

Overview

2
2
years of professional experience
1
1
Certification

Work History

AI Engineer

Trulogik
06.2024 - Current
  • AI Agent Development: Designed and deployed AI agents using LangChain, LangGraph, and Camel AI for automating medical document processing.
  • OCR Pipeline for Medical Documents: Built a scalable OCR pipeline using Azure Form Recognizer and PyTesseract for extracting data from CMS-1500, UB-04, EOBs, and lab reports.
  • RAG-based Medical Summarization: Developed a Retrieval-Augmented Generation (RAG) system for summarizing patient records, claims, and medical history using LLMs like LLaMA 3 and Phi 3.
  • Vector Database for Medical Claims: Integrated FAISS, ChromaDB, and Azure Cognitive Search to enable vector search for insurance claims, provider contracts, and medical records.
  • LangChain Multi-Agent System: Implemented a multi-agent system for document extraction, classification, and summarization, ensuring structured outputs for downstream applications.
  • FHIR Data Extraction & Population: Extracted structured data from 1M+ lab reports and integrated it into a FHIR database, enabling easy access for insurance and healthcare providers.
  • Automated Invoice & Ratesheet Processing: Built an AI-powered extraction system to parse insurance ratesheets and invoices from PDFs, Word, and Excel files using NLP and vector search.
  • AI-Powered Claims Processing: Designed an AI-driven workflow for claims adjudication, fraud detection, and provider-patient matching, improving processing efficiency.

Data Scientist (Advance Data Analyst)

Hyster-Yale Group
07.2023 - 07.2024
  • Implemented a Customer Churn prediction model, reducing customer churn by 26% and providing actionable insights for analysis.
  • Utilized NLP text information extraction techniques to automate warranty claim processing, resulting in a 53% reduction in the risk of fault claims.
  • Developed interactive Power BI dashboards encompassing economic indicators, customer churn analysis, warranty insights, and fleet prediction, facilitating data-driven decision-making across departments.
  • Orchestrated the deployment of the chatbot on the Azure platform, specifically tailored for SQL database integration, ensuring seamless operation and scalability to accommodate evolving business needs.
  • Developed predictive models to forecast fleet maintenance needs and optimize scheduling, contributing to a 65% reduction in downtime and associated costs.
  • Presented findings and recommendations to senior management through comprehensive reports and data visualizations, facilitating informed decision-making and driving continuous improvement initiatives.

Data Science Intern

iNeuron.ai
11.2022 - 07.2023
  • Developed a Text Summarization Application utilizing OpenAI's GPT-based language model and Streamlit framework. Integrated with Excel data inputs to generate concise summaries for stakeholders, aiding in efficient decision-making processes.
  • Created a Document Question Answering System employing OpenAI's advanced NLP capabilities and Streamlit for the user interface. Enabled stakeholders to upload documents and receive accurate responses to their queries, enhancing information retrieval efficiency.

Education

Master of Technology (M.Tech) - Artificial Intelligence

SIT - Symbiosis Institute of Technology
06.2024

Bachelor of Technology (B.Tech) - Information Technology

SIT - Symbiosis Institute of Technology
01.2022

Skills

  • TensorFlow
  • PyTorch
  • OpenAI
  • Hugging Face
  • LangChain
  • LangGraph
  • Camel AI
  • Python
  • SQL
  • JavaScript
  • FAISS
  • ChromaDB
  • PostgreSQL
  • Power BI
  • Tableau
  • GPT models
  • RAG pipelines
  • Llama 3
  • Hugging Face Transformers
  • FHIR
  • EHR
  • EDI
  • Microsoft SQL server
  • Machine learning
  • Data modeling
  • Software engineering
  • Natural language processing
  • Reinforcement learning
  • Statistical modeling
  • Dimensionality reduction
  • Git

Certification

  • The Full Stack (Meta), 11/01/23
  • SQL for Data Science (UC Davis, Coursera), 01/01/23

Languages

English
Hindi

Timeline

AI Engineer

Trulogik
06.2024 - Current

Data Scientist (Advance Data Analyst)

Hyster-Yale Group
07.2023 - 07.2024

Data Science Intern

iNeuron.ai
11.2022 - 07.2023

Bachelor of Technology (B.Tech) - Information Technology

SIT - Symbiosis Institute of Technology

Master of Technology (M.Tech) - Artificial Intelligence

SIT - Symbiosis Institute of Technology
Shubham Raj