Skip to content
View Narenderbeniwal's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report Narenderbeniwal

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Narenderbeniwal/README.md

πŸ‘‹ Hi, I'm Narender Kumar

πŸš€ Data Scientist @ KPMG | Generative AI | Agentic AI | Azure | Python | NLP | MLOps

🎯 AI Engineer with 5+ years of experience building and deploying production-grade machine learning and Generative AI systems. Passionate about designing agentic workflows, LLM-powered platforms, and customer intelligence engines at scale.


🧠 About Me

  • πŸ‘¨β€πŸ’Ό Currently at KPMG, delivering enterprise AI solutions for telecom and BFSI clients
  • πŸ€– Building Agentic AI systems to automate decision-making and business processes
  • πŸ“„ Leading GenAI-powered document automation using LLaMA 3, RAG, PEFT, and LoRA
  • 🌐 Architecting multilingual customer platforms with ChatGPT API + Azure
  • πŸ› οΈ Driving MLOps transformations using Azure DevOps, Functions, and containerized workflows
  • πŸ“ˆ Delivering measurable impact via predictive analytics, recommendations, and dashboards

πŸ’‘ What I Do

πŸ”Ή Enterprise Generative AI

  • Developed multi-lingual summarization, sentiment analysis, and intent detection systems using ChatGPT, Azure OpenAI, and custom LLMs
  • Built automated support and insights engines reducing resolution time by 70%

πŸ”Ή Agentic AI Frameworks

  • Implemented intelligent multi-agent pipelines using the Agno framework for finance and telecom
  • Designed autonomous agents for churn prediction, lead scoring, and journey mapping

πŸ”Ή MLOps & Scalable ML

  • Deployed ML solutions using Azure Functions, CI/CD Pipelines, and Dockerized APIs
  • Reduced compute latency by 80% by migrating legacy ML pipelines to cloud-native infrastructure

πŸ› οΈ Technical Skill Stack

Domain Tools & Technologies
Languages Python, SQL, JavaScript
ML/AI Scikit-Learn, XGBoost, Deep Learning, Recommender Systems
GenAI & NLP ChatGPT, OpenAI API, LangChain, RAG, LLaMA 3, PEFT, LoRA
Agentic AI Agno, Multi-agent Systems, Reasoning Agents
Cloud & MLOps Azure, Azure DevOps, Docker, Flask, Azure Functions
Databases MySQL, MongoDB
Dashboards Power BI
Frontend HTML, CSS, JavaScript

πŸ”­ Currently Building

  • βš™οΈ AI document drafting engines with LLaMA 3, PEFT, and LoRA
  • πŸ’¬ Multilingual customer insight platform powered by GenAI
  • 🧠 Reusable agentic workflows and accelerators for enterprise AI use

🧰 Tools I Use


πŸ† GitHub Stats & Highlights

GitHub Streak
GitHub Stats
GitHub Trophies


🀝 Let’s Collaborate

  • 🎯 Enterprise GenAI & Agentic AI platforms
  • ☁️ Azure-based MLOps & scalable deployments
  • πŸ“Š Data strategy & end-to-end ML implementation

🌐 Connect with Me

LinkedIn
GitHub


🧠 β€œDriven by data, shaped by intelligence, and scaled with code.”

Popular repositories Loading

  1. Data-Science-Hnad-Written-Notes Data-Science-Hnad-Written-Notes Public

    4

  2. wafer_circleci-main wafer_circleci-main Public

    The inputs of various sensors for different wafers have been provided. In electronics, a wafer (also called a slice or substrate) is a thin slice of semiconductor used for the fabrication of integr…

    Python 2

  3. Predict-Crime-Rate-in-Chicago-Facebook-Prophet- Predict-Crime-Rate-in-Chicago-Facebook-Prophet- Public

    # - The Chicago Crime dataset contains a summary of the reported crimes occurred in the City of Chicago from 2001 to 2017. - Dataset has been obtained from the Chicago Police Department's CLEAR (Ci…

    Jupyter Notebook 1

  4. BreastCancerPrediction_Azure BreastCancerPrediction_Azure Public

    HTML 1 1

  5. Data-Science-Books Data-Science-Books Public

    1

  6. Spark-By-Example Spark-By-Example Public

    1 1