Resume

Umer Khan

Founding AI engineer building production-grade AI systems from the ground up. Specializing in GDPR-compliant RAG systems, AI-powered automation, and scalable data architectures with Python, FastAPI, LangChain, and AWS.

Berlin, Germany

Experience

4 positions

Bloomers Berlin

Founding Engineer

Jan 2025 — Jan 2026
Berlin
  • Led end-to-end migration from Squarespace to Shopify, including data pipeline design, API integrations, and deployment driving 200-250% increase in monthly orders.
  • Built an AI-powered content migration workflow using LangChain agents to automatically migrate and transform 500+ product pages from legacy Squarespace to Shopify, reducing manual effort by 90%.
  • Designed a GDPR-compliant RAG system integrating BioGPT with medical test results and physician recommendations.
  • Optimized Google Ads and Merchant Center feeds through automated bidding algorithms and product data enrichment, achieving 4.9x ROAS.
  • Developed a personal Shopify storefront MCP and managed an Orchestrator with LangGraph for daily automation workflow tasks.
LangChain LangGraph RAG Shopify MCP BioGPT GDPR Google Ads Python

Comparado GmbH (Idealo Group)

Data Engineer

Feb 2024 — Aug 2024
Berlin
  • Standardised and simplified ETL pipelines to reduce historical grown technical debt.
  • Supported migration of BI infrastructure to AWS.
  • Extended first party tracking by adding attribution to new marketing channels like Google CSS-PLA and Bing.
  • Worked closely with Idealo legal and data governance teams to reduce the footprint of shared Data Lake and ensure DSA/DMA compliance.
  • Migrated AB Testing to Growthbook.
AWS ETL Growthbook DSA/DMA Google CSS-PLA Data Governance BI

CorAI (Bernstein Analytics)

Cloud Solutions Architect

Dec 2022 — Jan 2024
Berlin
  • Developed a simple and inexpensive architecture to gather 1 million daily news articles globally, extracted policy-related news, and delivered via standardized API.
  • Applied NLP models for precise article categorization and sentiment analysis.
  • Delivered production-grade APIs for the product team to access the data and build a product on top of it.
  • Collaborated closely with external stakeholders (NewsCatcher, Bernstein Group, Axel Springer).
NLP Sentiment Analysis REST APIs News Data Python AWS Stakeholder Management

Teradata

Data Engineer

Jan 2018 — Dec 2021
Karachi
  • Worked in a data-focused agency, delivering high-quality data solutions for the largest telecom companies in Pakistan.
  • Enhanced data ingestion pipelines to improve efficiency and accuracy.
  • Developed ETL pipelines for Telenor Pakistan, integrating new data flows with Kafka.
Kafka ETL Teradata Telecom Data Pipelines SQL

Technical Stack

Core skills

AI & ML

LLM Engineering RAG Systems LangChain LangGraph MCP AI Agents PyTorch NLP

Data & Backend

Python FastAPI PostgreSQL MongoDB Kafka ETL/ELT

Cloud

AWS S3 Lambda Glue Athena EMR Docker

Observability

LangSmith Grafana Prometheus

Education

Bachelor of Science

University of Karachi, Pakistan

2014 — 2018

Certifications

Stepping into Leadership

Idealo Group

AWS Cloud Solutions Architect

Amazon Web Services

Data Science with ML/AI

IBM

Contact

Get in touch

Open to AI engineering roles and consulting opportunities.

Get in touch