Skip to content
View shaikfakruddin2018's full-sized avatar

Block or report shaikfakruddin2018

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 is supported. 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
shaikfakruddin2018/README.md
Shaik Fakruddin — Data & Analytics Engineer

Portfolio


Shaik Fakruddin

Portfolio LinkedIn Email

  

Hi, I'm Shaik 👋

I build data systems that scale — from raw ingestion to business-ready models. My focus is the modern data stack: reliable ELT on Snowflake, clean and tested dbt models, and semantic layers that give teams one source of truth.

I'm now extending that foundation into trustworthy AI — my MSc thesis tackles uncertainty calibration in retrieval-augmented LLMs: whether a model's confidence can be trusted for risk-sensitive decisions, and how embedding quality shapes that reliability (LLM-as-judge, retrieval metrics, LangChain & LangGraph).


🟢 Open to work  ·  Germany · Netherlands · Switzerland · Austria · Ireland  ·  Remote / Hybrid / Relocation

What I Build

⚙️  Data Pipelines

Robust ELT pipelines on Snowflake — tested, monitored, and built to be trusted in production.

📐  Analytics Engineering

Clean, documented dbt models and semantic layers that give analysts a single source of truth.

🤖  AI on Data

RAG pipelines with LangChain, Chroma & FAISS — rigorously evaluated with LLM-as-judge and retrieval metrics (MRR, nDCG, recall, precision).

Skills

🏗️  Data Engineering
& Analytics

Snowflake dbt Python SQL
ELT Testing Semantic Layer
📐  Data Modeling

Dimensional Data Mesh
🤖  AI / GenAI

LLMs RAG LangChain LangGraph Chroma FAISS
LLM-as-Judge Retrieval Metrics Cortex
📊  BI & Tooling

Power BI AWS Git CI/CD

Projects — by Target Role

Work mapped to the roles I'm targeting. ✅ Live links to code; 🔜 Coming soon is on the near-term roadmap.

📊 Data Analyst

Project Stack Status
Executive Sales Intelligence Dashboard — KPIs, segmentation, forecasting, drill-through Power BI · SQL · Python · Snowflake 🔜 Coming soon
Customer Churn Analytics Platform — churn prediction, cohorts, CLV, root-cause Python · SQL · Power BI · Snowflake 🔜 Coming soon

🏗️ Data Engineer

Project Stack Status
Enterprise Retail Data Mesh — ELT, RBAC, data quality, IaC, CI/CD Snowflake · dbt · Terraform · GitHub Actions ✅ Live
Streaming Data Lakehouse — real-time ingestion, stream processing, governance Snowflake · Kafka · Python · Terraform 🔜 Coming soon

📐 Analytics Engineer

Project Stack Status
Enterprise Retail Data Mesh — dbt medallion, domain data products, semantic layer dbt · Snowflake · Cortex AI · Streamlit ✅ Live
Modern Metrics Layer — reusable business metrics, data contracts, lineage, tests dbt · Snowflake · Semantic Views · Streamlit 🔜 Coming soon

🤖 AI Engineer

Project Stack Status
Operations Copilot — NL→SQL, semantic search, AI-explained results Cortex Analyst · Streamlit · OpenAI ✅ Live
RAG Uncertainty Calibration — MSc thesis, LLM-as-judge, calibration RAG · FAISS · scikit-learn ✅ Live
Enterprise RAG Platform — document KB, vector search, citations, chat Cortex Search · Vector Search · Streamlit · Python 🔜 Coming soon

BGE beat OpenAI embeddings · isotonic calibration cut ECE ~32% — see the thesis repo. Roadmap projects ship when they meet the quality bar.


GitHub Activity

 



Let's Talk

I'm open to Data Engineering · Analytics Engineering · AI Engineer roles across Europe. The fastest way to reach me:

Connect on LinkedIn   Send an Email


Thanks for stopping by — let's build something reliable.

Popular repositories Loading

  1. operations-copilot operations-copilot Public

    Natural-language analytics for enterprise operations: Snowflake Cortex Analyst (NL to SQL) + OpenAI executive summaries on a governed semantic layer. Streamlit app.

    Python 1

  2. rag-uncertainty-calibration rag-uncertainty-calibration Public

    MSc thesis: evaluating & improving uncertainty calibration in retrieval-augmented LLMs. Compares 5 embedding models (BGE beats OpenAI) and cuts ECE ~32% via isotonic regression on real financial fi…

    Jupyter Notebook 1

  3. enterprise-retail-data-mesh-snowflake enterprise-retail-data-mesh-snowflake Public

    Enterprise retail Data Mesh on Snowflake: domain data products (dbt medallion), governance-as-code (Terraform, tags, masking, row-access), Snowflake Cortex AI, and a Streamlit BI + AI Copilot.

    Python 1

  4. shaikfakruddin2018 shaikfakruddin2018 Public

    Config files for my GitHub profile.

  5. Project-Portfolio Project-Portfolio Public

    Jupyter Notebook

  6. BabaFakruddinShaikProject.github.io BabaFakruddinShaikProject.github.io Public

    CSS