Open to opportunities

Jayant Bisht

@jayantbisht

Message

Data Engineering & ML Engineer building Databricks lakehouse ETL and RAG systems for accurate, fast question answering.

India

Message

What I'm looking for

I’m looking for a role where I can build end-to-end data pipelines and deploy ML/RAG systems—working with Databricks, AWS, and production-ready APIs—so models and data products stay reliable as they scale.

I built 3+ scalable Databricks ETL pipelines at Lirik Infotech Pvt. Ltd. using PySpark and Delta Lake, integrating 5+ sources into a unified lakehouse while cutting manual handling time by 40%.

I’ve also shipped ML end-to-end: at Physics Wallah Pvt. Ltd. I delivered a production-ready Python model with 90%+ accuracy, then set up GitHub Actions CI/CD to deploy it on AWS EC2 for real-time inference under 200ms.

On the product side, I designed a hybrid RAG SEBI Document QA System with dense + sparse retrieval, FastAPI multi-LLM support, and Qdrant Cloud, validating quality with RAGAS (0.89 answer relevancy) and 100% context recall.

Experience

Work history, roles, and key accomplishments

Data Analytics & Engineering Intern

Lirik Infotech Pvt. Ltd.

Nov 2025 - May 2026 (6 months)

Designed and deployed 3+ scalable ETL pipelines on Databricks using PySpark and Delta Lake, automating end-to-end data ingestion and transformation workflows. Built multi-source ETL workflows integrating 5+ data sources into a unified lakehouse architecture, reducing manual data handling time by 40%.

PySpark Databricks Delta Lake ETL S3 Kafka Azure Blob Storage Power BI

Machine Learning Intern

Physics Wallah Pvt. Ltd.

Jun 2024 - Aug 2024 (2 months)

Built and deployed an end-to-end machine learning model achieving 90%+ accuracy, using modular and production-ready Python code. Designed and implemented a CI/CD pipeline using GitHub Actions, deploying models on AWS EC2 for real-time inference with less than 200ms latency.

Python scikit learn EC2 GitHub Actions CI CD Feature Engineering Hyperparameter Tuning