Skip to content
View somesh-ghaturle's full-sized avatar
🐼
Exploring
🐼
Exploring

Highlights

  • Pro

Block or report somesh-ghaturle

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

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

Report abuse
somesh-ghaturle/README.md
Typing Animation
Hero Banner

AI and Data Engineer with 5+ years delivering AI and analytics solutions across enterprise, retail, and automotive, impacting over $2M in business value. Currently building production agentic AI systems (LangGraph, A2A, RAG) on Databricks, with LoRA/QLoRA fine-tuning and MLflow-based MLOps.


How I Build

How I think about a data platform — raw landing zone to decision-ready product.

Bronze

Ingest

Silver

Refine

Gold

Activate

Batch and real-time ingestion with Spark, AWS Glue, and Azure Data Factory — landing structured and unstructured enterprise data reliably.

Cleaning, conforming, and dimensional modelling on Delta Lake and Snowflake, with data governance and quality checks built in.

Decision-ready output: RAG systems, multi-agent workflows, dashboards, and deployed models.

Agentic Systems Data Platforms Delivery Mindset

Contribution Snake

🐍 A snake eating its way through my GitHub contribution graph — every square it swallows is a day I shipped code. Regenerated every day at midnight by GitHub Actions, and it adapts to your light/dark theme.

Snake eating my GitHub contribution graph
Updates daily Powered by GitHub Actions

About Me

  • 🏢 AI Engineer building agentic workflows in LangGraph and LangChain served as FastAPI microservices, and an LLM document intelligence system over 15M+ documents on Azure Databricks
  • 🚗 Experience across enterprise, retail, and automotive: LLM agents on an enterprise GenAI platform, AWS Glue pipelines, and a 10TB+ Hadoop to Synapse/Snowflake migration
  • 🧠 Designed and deployed 15+ ML models and pipelines processing 10TB+ of enterprise data
  • ⚙️ Fine-tuning Llama 3 and Mistral with LoRA/QLoRA, serving with vLLM, shipping with MLflow and Databricks Workflows
  • 🎓 M.S. Data Science, Pace University; research: FAIR-Agent (SARD 2025)
  • 💬 Open to AI Engineer, Agentic AI Engineer and GenAI Engineer roles
Core focus
Agentic AI
RAG systems
LLM fine-tuning
MLOps
Data engineering

Featured Projects

Project What it shows
Trust Control Center — The $1 Trillion AI Problem Django platform that detects, visualizes, and resolves cross-source metric inconsistencies, the root cause of unreliable AI predictions
Agentic AI Systems Open-source reference of agentic architectures: multi-agent orchestration, tool use, and RAG patterns with LangGraph and LangChain
FAIR-Agent Multi-agent RAG research (SARD 2025) that improved faithfulness 17.4% on financial and medical benchmarks
Autonomous-Multi-Agent-Research-Action-System Multi-agent orchestration and research workflows

GitHub Activity

📈 Streak and contribution curve for the past year. The curve is rendered by my own workflow straight from the GitHub GraphQL API — no third-party service to go dark on me — and follows your light/dark theme.

GitHub Streak
Contribution activity over the past year

Tech Stack

Languages

Python SQL PySpark R Java C++

AI and Machine Learning

LangGraph LangChain LlamaIndex PyTorch scikit-learn MLflow Hugging Face TensorFlow vLLM OpenAI

Data Engineering

Apache Spark Snowflake Delta Lake Hadoop Pandas

Cloud and Analytics

Azure Databricks AWS GCP BigQuery Power BI Tableau

DevOps and MLOps

Docker FastAPI Ray GitHub Actions Terraform

Methodologies

Agile MLOps Data Governance


Current Focus

  • Production agentic AI systems with LangGraph, A2A, and RAG on Databricks
  • LoRA/QLoRA fine-tuning of open models and low-latency serving with vLLM
  • MLflow-based MLOps: model registry, workflows, and monitoring
  • RAG evaluation with Ragas and LangSmith

Certifications

Databricks for Generative AI · AWS Databricks Platform Architect · Azure AZ-900 · DP-900 · AI-900 · PL-900 · PG Diploma in Full Stack Data Science


Contact

If you want to talk about AI systems, data engineering, or open roles, reach out here:

Footer

Popular repositories Loading

  1. 30-Days-Of-Python 30-Days-Of-Python Public

    Forked from Asabeneh/30-Days-Of-Python

    30 days of Python programming challenge is a step-by-step guide to learn the Python programming language in 30 days. This challenge may take more than100 days, follow your own pace.

    Python 2 1

  2. Data-Science--Cheat-Sheet Data-Science--Cheat-Sheet Public

    Forked from georgearun/Data-Science--Cheat-Sheet

    Cheat Sheets

    TeX 1

  3. MachineLearningNotebooks MachineLearningNotebooks Public

    Forked from Azure/MachineLearningNotebooks

    Python notebooks with ML and deep learning examples with Azure Machine Learning | Microsoft

    Jupyter Notebook 1

  4. somesh-ghaturle somesh-ghaturle Public

    Repo for my profile Description

    1 2

  5. swot swot Public

    Forked from JetBrains/swot

    Identify email addresses or domains names that belong to colleges or universities. Help automate the process of approving or rejecting academic discounts.

    Kotlin 1

  6. awesome-generative-ai-guide awesome-generative-ai-guide Public

    Forked from aishwaryanr/awesome-generative-ai-guide

    A one stop repository for generative AI research updates, interview resources, notebooks and much more!

    1