Skip to content
View ankit-khare-2015's full-sized avatar

Block or report ankit-khare-2015

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. 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
ankit-khare-2015/README.md

👋 Hi, I'm Ankit Khare

AI & Data Architect with over a decade of experience building scalable, real-world solutions using data engineering, AI/ML, and cloud-native technologies.
Based in Hannover, Germany 🇩🇪 | Open to collaboration & new opportunities


💼 About Me

  • I’m currently working on building end-to-end RAG (Retrieval-Augmented Generation) solutions using Azure OpenAI, LangChain, and ChromaDB, and creating content for optimizing power bi reporting solutions
  • I’m currently learning LangGraph, LLMOps, and vector database optimization for production AI systems.
  • I’m looking to collaborate on data/AI platform modernization, streaming pipelines, and MLOps infrastructure projects.
  • Ask me about:
    • Building scalable Data Mesh / Lakehouse architectures
    • Real-time ingestion using Kafka & Spark
    • Operationalizing GenAI in enterprise with RAG pipelines and MLOps
  • How to reach me: ankit.khare.2015@gmail.com | LinkedIn
  • I am humbled at: I’ve repeatedly optimized analytics data pipelines and reporting solutions in under three weeks, significantly improving team efficiency and driving higher user adoption.

🔧 Tech Stack

Languages: Python, SQL, Scala
AI & ML: Azure OpenAI, LangChain, LangGraph, MLflow, PyTorch
Big Data: Apache Spark, Kafka, Databricks
Cloud: Azure, Azure Synapse, Azure ML, Azure Event Hub
Data Tools: dbt, Airflow, Delta Lake, Power BI
DevOps: Docker, Terraform, CI/CD pipelines


📌 Repositories

Watch this space! I’m currently creating projects in the following areas:

  • End-to-end AI applications and RAG pipelines
  • Understanding and implementing AI guardrails and safety systems
  • Exploring post-training strategies and terminology
  • Working with diffusion models and generative AI architectures
  • Getting started with LangChain and building intuitive AI agents
  • Creating dummy use cases across various domains like:
    • Airline (e.g., predictive maintenance, intelligent customer support)
    • Energy (e.g., anomaly detection, real-time grid analytics)
    • Business Assurance (e.g., revenue assurance using audit platforms)
    • Dairy Industry (e.g., milk quality prediction, supply chain AI)

These projects will cover core concepts in data platforms, AI integration, and scalable data engineering.

Pinned Loading

  1. user-activity-real-time-ingestion user-activity-real-time-ingestion Public

    This project implements a fully automated, containerized real-time data processing pipeline for user activity tracking. It leverages Kafka, PostgreSQL, Grafana, and Python-based producer/consumer s…

    Python 1

  2. DataOps-Animal-Nutrition DataOps-Animal-Nutrition Public

    Learn DataOps by building a complete data pipeline with Airflow, dbt, PostgreSQL, and Grafana using real-world animal nutrition data. Automate, monitor, and understand DataOps principles with hands…

    Python 2 1

  3. energy-meter-metrics energy-meter-metrics Public

    Built a small Energy Analytics project using dbt, PostgreSQL, and Grafana. It analyzes smart meter data (energy usage, voltage, cost) using dbt models and visualizes key metrics via Grafana. Seeded…

    1

  4. iceberg-minio-spark-playground iceberg-minio-spark-playground Public

    A hands-on playground for Apache Iceberg with MinIO and Spark, showcasing modern data lakehouse concepts. Includes Docker setup, sample data, and SQL queries to explore table versioning, schema evo…

    Jupyter Notebook

  5. docker-learn-by-doing docker-learn-by-doing Public

    A beginner-friendly project to practice Docker step by step with images, containers, ports, env vars, and volumes.

    Python 1 1

  6. data-vault-modelling data-vault-modelling Public

    Data Vault 2.0 made simple. This project uses a fashion retail example with dbt, PostgreSQL, and Grafana to explain hubs, links, satellites, PIT, and marts showing how Data Vault builds flexible, a…