GenAI Medical Summarization
Automated system for summarizing complex medical documents using Generative AI. Streamlines information extraction for healthcare professionals to improve patient care.
Hi, my name is
I'm a Senior Data Engineer with 4+ years of experience specializing in building scalable data pipelines and infrastructure. Currently working at Sevaro, solving real-world problems through data engineering and AI.
Hello! I'm Anchit, a Senior Data Engineer specializing in GenAI and Cloud-Native Analytics. I enjoy building scalable data platforms and integrating Generative AI solutions to solve complex business problems.
With over 4 years of experience, I've worked across the full data lifecycle - from building MDM pipelines for pharmaceutical giants to developing LLaMA-based gaming bots and automating medical document summarization.
My background includes an M.Tech in CS from IIIT Delhi and deep expertise in the modern data stack. I'm constantly exploring new technologies in the AI/ML space to build more intelligent systems.
Here are some technologies I use daily:
Oct 2025 — Present
@ Sevaro Health
Jul 2024 — Oct 2025
@ Junglee Games
Jul 2023 — Jul 2024
@ Junglee Games
Oct 2022 — Jul 2023
@ Junglee Games
Apr 2022 — Sep 2022
@ Axtria
Jul 2021 — Apr 2022
@ Axtria
Master of Technology
2019 — 2021
Specialized in Computer Science with focus on Natural Language Processing and Deep Learning. Worked on research projects involving semantic analysis and information retrieval.
GATE Score: 98.14Bachelor of Technology
2014 — 2018
Completed B.Tech in Computer Science with First Division. Developed foundational skills in programming, Android development, and machine learning.
First DivisionAutomated system for summarizing complex medical documents using Generative AI. Streamlines information extraction for healthcare professionals to improve patient care.
Integrated LLaMA models into gaming environments to create intelligent, responsive bots that enhance player engagement at Junglee Games.
Enterprise Master Data Management pipeline processing 50M+ records. Implemented fuzzy matching and NLP for high-accuracy entity resolution.
NLP-based Chrome Extension to find semantically similar sentences in cited documents for Wikipedia citations using deep learning embeddings.
Text classification system to detect humor using deep learning embeddings, optimized for memory-sensitive mobile devices with model size <10 MB.
Android application to help users locate blood banks across India. Features real-time availability and location-based search.
Technical articles on Data Engineering, Apache Spark, and AI/ML
Apache Spark 4.1 is packed with features designed to make data engineering faster, more flexible, and more efficient...
Data engineering is one of the most in-demand roles in tech. With the rise of GenAI and real-time analytics, the role is evolving...
The real power of a Lakehouse comes from how you handle unstructured data. In this article, we explore best practices...
Apache Arrow is a cross-language platform for in-memory data that specifies a standardized column-oriented format...
Apache Spark 4.0 is on the horizon, bringing major changes to the world of big data processing...
Building a data engineering portfolio is one of the most important things you can do to stand out in a crowded job market...
Score: 98.14 Percentile
Databricks
DeepLearning.AI
Astronomer
Udemy
Microsoft
Oracle
06. What's Next?
I'm currently open to new opportunities and exciting projects. Whether you have a question or just want to say hi, my inbox is always open. I'll try my best to get back to you!