Anubhav Sharma
AI / Data Engineer | GenAI, LLM Pipelines & Data Engineering
Pune
Summary
Data / AI Engineer building production generative AI pipelines, data lakehouses, and automation for 61+ companies across financial-data and credit-analytics workflows. Designs self-verifying LLM extraction systems for 25–75 financial documents per week that improved document accuracy by 16+ percentage points to 90%+ and made extracted metrics traceable for analyst review. Architected scalable ingestion, MLOps, and CI/CD tooling across Delta Lake, MinIO, Airflow, DVC, MLflow, and Docker.
Overview
1
1
Language
3
3
years of professional experience
Work History
Data / AI Engineer
CCR Technologies Pvt. Ltd.
Pune
09.2024 - Current
- Architected a Bronze / Silver / Gold layered data lake house (Delta Lake + Polars) on a self-hosted Minio object store on on-prem servers, with automated backup to AWS S3; ingested daily price and volume data (Alpha Vantage, FMP) for 20,000+ tickers with incremental transforms and a point-in-time dataset for machine learning.
- Delivered validated metrics for 60+ private companies to internal credit-surveillance dashboards, enhancing analyst review efficiency with OCR-based PDF snapshots.
- Automated near-real-time ingestion of broker research reports (Goldman Sachs, J.P. Morgan, Morgan Stanley, UBS, Wells Fargo, TD Cowen, Bank of America, Jefferies) through email and website scraping with LLM entity resolution and sentiment analysis; migrated the pipeline to GitLab CI / CD.
- Set up MLOps tooling — DVC for dataset and experiment versioning, MLflow for tracking, and Docker for containerized experiments — and ran A/B tests of local versus hosted LLMs with monitoring dashboards, reducing inference cost.
- Automated near-real-time ingestion of broker research reports through email and website scraping with LLM entity resolution and sentiment analysis; migrated pipeline to GitLab CI / CD for improved reliability.
- Built 15+ resilient web-scraping pipelines (GPU, memory, RAM and fertilizer pricing; syndicated-loan and credit-document sync) with automated retries and Teams / email alerts, scheduled on Apache Airflow; migrated core processes to a Linux virtual machine to scale throughput.
- Built 15+ resilient web-scraping pipelines for GPU, memory, and RAM pricing data with automated retries and alerts via Teams/email, scheduled on Apache Airflow, while migrating core processes to a Linux virtual machine to increase throughput.
Data Analyst Intern
CCR Technologies Pvt. Ltd.
Pune
03.2024 - 05.2024
- Built automated Python pipeline (Beautiful Soup + Selenium Web Driver) to scrape company layoff data from 10+ websites, detecting new records through database comparison and writing daily updates to SQL database, eliminating manual collection task.
- Developed automated scraper to incrementally collect filings data from U.S. SEC website, enhancing data accessibility for analysis.
- Authored 5+ Apache Airflow DAGs to orchestrate production Python jobs and refactored existing codebase for improved readability and structure.
Data Analyst Intern
Polestar Solutions & Services India Pvt. Ltd.
Kolkata
06.2023 - 08.2023
- Executed data modeling within industry-grade data-warehouse architecture to support data analysis needs.
- Developed SQL scripts to populate hierarchy tables and address special-case transformations for data accuracy.
- Imported raw CSV data into SQL Server (SSMS) and designed 15+ staging, fact, and dimension tables to enhance data organization.
- Performed data modeling within an industry-grade data-warehouse architecture.
Education
B.Tech - Computer Science and Engineering
B.P. Poddar Institute of Management and Technology
Kolkata, West Bengal, India01-2024
ISC (Class XII) - undefined
Salt Lake School
Kolkata, West Bengal, India01-2020
ICSE (Class X) - undefined
Salt Lake School
Kolkata, West Bengal, India01-2018
Skills
Python
SQL
Delta Lake
Apache Airflow
Docker
FastAPI
Data modeling
ETL pipelines
Lakehouse architecture
Data validation
Retrieval-augmented generation
Timeline
Data / AI Engineer
CCR Technologies Pvt. Ltd.
09.2024 - Current
Data Analyst Intern
CCR Technologies Pvt. Ltd.
03.2024 - 05.2024
Data Analyst Intern
Polestar Solutions & Services India Pvt. Ltd.
06.2023 - 08.2023
ICSE (Class X) - undefined
Salt Lake School
ISC (Class XII) - undefined
Salt Lake School
B.Tech - Computer Science and Engineering
B.P. Poddar Institute of Management and Technology