About Me

GitHub /
Google Scholar /
Hugging Face /
LinkedIn

Hello! I am Vipul Mehra. I am an experienced Machine Learning Practitioner skilled in building models for Natural Language, Recommender Systems, Search, Ranking, and Computer Vision.

With over 10+ years of industry experience, I bring expertise in machine learning and building low-latency high-throughput machine learning systems and platforms.

I have a proven track record of building and delivering high-impact machine learning/AI models that drive business value and ROI, along with end-to-end systems that scale to millions of users.

I am currently exploring Large Language Models (LLMs) and Large Vision Models (LVMs), with a focus on optimizing model serving, scaling, fine-tuning techniques and integration into real-world applications across ranking, recommendations, agentic AI workflows, and Retrieval-Augmented Generation (RAG) pipelines.

Let us connect to explore how I can contribute my skills and experience to make a meaningful impact.

Research & Projects

See all

Shop-The-Room: A Zero-Shot Foundation Model Framework for Visual Discovery in E-Commerce

May 29, 2026

Shanthakumar, V. A., Barnett, C., Mehra, V., Chanprapan, K., Shankar, R., & Mukherjee, T. (2026, April). Shop-The-Room: A Zero-Shot Foundation Model Framework for Visual Discovery in E-Commerce. In The International FLAIRS Conference Proceedings (Vol. 39, No. 1).
Multi-label Lung Disease Detection Using Deep Learning

May 28, 2026

Kansara, S., Shah, P., Swain, D., Kumar, M., & Mehra, V. (2025, November). Multi-label Lung Disease Detection Using Deep Learning. In International Conference on Data Science, Computation and Security (pp. 111-123). Cham: Springer Nature Switzerland.
Machine Learning for Stroke Detection: Performance Evaluation of Random Forest and XGBoost Classifiers.

Mar 06, 2025

Deshmukh, O., Swain, N. K., Panda, T., Swain, D., Mehra, V., & Kumar, M. (2025, November). Machine Learning for Stroke Detection: Performance Evaluation of Random Forest and XGBoost Classifiers. In 2025 IEEE 3rd International Symposium on Sustainable Energy, Signal Processing and Cybersecurity (pp. 1-4). IEEE.
GuavaNet: A deep neural network architecture for automatic sensory evaluation to predict degree of acceptability for guava by a consumer.

Mar 03, 2025

Mehra, V. (2021). GuavaNet: A deep neural network architecture for automatic sensory evaluation to predict degree of acceptability for Guava by a consumer. arXiv preprint arXiv:2108.02563.
Hand Gesture Recognition using Support Vector Machine and Bag of Visual Words model

Mar 02, 2025

Exploring SVM for Hand Gesture Recognition

Latest Blog Posts

See all

Exploring MCP, Tools and Agents.

May 28, 2025

My stab at building agentic AI workflows and MCP servers and connecting them with tools.
ML Algorithms from scratch

Mar 01, 2025

Classic ML algorithms from scratch with just python and numpy!
Recommender Systems and Ranking

Mar 01, 2025

All my thoughts around building and scaling recommender and search and ranking systems
So you think you know NDCG?

Mar 01, 2025

Deep dive into NDCG as a ranking metric

Press Esc or click anywhere to close