Skip to content
View zohaibNaseem's full-sized avatar
1 follower · 1 following

Block or report zohaibNaseem

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. 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
zohaibNaseem/README.md

Rana Zohaib Naseem Khan

Data Engineer in Islamabad, Pakistan. I build data pipelines for US healthcare claims and payments data. I also build retrieval-augmented generation (RAG) applications with LLMs.

Experience

Data Engineer, Biome Analytics (March 2025 to present)

  • Work with US healthcare revenue-cycle data under HIPAA rules.
  • Migrated data pipelines from Spark to Ibis.
  • Built a service that loads 500 million records from the data lake into the database. The service uses parallel processing.
  • Built data quality checks for the pipelines.
  • Tools: Python, SQL, Spark, Ibis, Databricks, Dagster, Azure (AKS).

Junior Software Engineer, Kalsoft (August 2024 to February 2025)

  • Built data analytics and AI products.
  • Data scraping, data cleaning and preprocessing.
  • Machine learning use cases and an OCR system for text extraction.

Projects

Project Description
underpayment-checker Compares insurance payments with the rates that insurers publish. A streaming parser reads multi-gigabyte rate files. DuckDB SQL layers apply the matching rules. 98 tests.
weather-etl-pipeline ETL pipeline from a public weather API to SQLite, with rolling statistics, anomaly detection, retries and run auditing.
pdf-rag-assistant RAG application for PDF documents with admin and user roles. LangChain, FAISS and Streamlit.

Skills

  • Languages: Python, SQL
  • Data processing: Spark, Databricks, Ibis, DuckDB, pandas
  • Orchestration: Dagster
  • Cloud: AWS, Azure (AKS)
  • LLM applications: LangChain, FAISS, Hugging Face embeddings, Groq
  • Healthcare data: claims and remittances (837/835), CPT codes, payer rate files (Transparency in Coverage)

Education

BS Computer Science, Capital University of Science and Technology (CUST), Islamabad. CGPA 3.99/4.00. University Gold Medal.

Pinned Loading

  1. underpayment-checker underpayment-checker Public

    Compares US insurance payments with the rates that insurers publish under Transparency in Coverage. Streaming JSON parser, DuckDB SQL layers, PDF report, 98 tests.

    Python

  2. pdf-rag-assistant pdf-rag-assistant Public

    RAG app for PDF documents with admin and user roles. LangChain, FAISS, Hugging Face embeddings, Groq LLM, Streamlit.

    Python

  3. weather-etl-pipeline weather-etl-pipeline Public

    Weather ETL pipeline: Open-Meteo API to SQLite with rolling statistics, anomaly detection, retries and run auditing.

    Python