Siddhant Bahuguna
Gurugram, Haryana, India
Summary
🤩
Rockstar🎓
Top SchoolSiddhant Bahuguna is a full-stack engineering leader with 4+ years of experience building scalable web platforms and automation pipelines across sustainability, fintech, and e-commerce domains. As Lead Fullstack Engineer at Terrascope he helped launch the company’s first Product Carbon Footprint product, driving lifecycle methodology, PACT conformance, and environmental impact tracking while combining Nest.js, React and AWS to deliver robust systems. He’s led cross-functional teams and large-scale services—from a smart meter Head End System handling lakhs of commands to a verification platform processing ~200k daily checks—streamlining deployments and onboarding through automation. A pragmatic contributor to open-source ML tooling, he implemented Faster R-CNN-based artifact detection for the popular docTR OCR project, bridging deep learning research and production inference. Based in Paris with roots in India, Siddhant blends hands-on engineering with product-minded architecture to ship measurable, sustainability-focused solutions.
4 years of coding experience
9 years of employment as a software developer
High School, Science, High School, Science at Mukherjee Memorial Senior Secondary SchoolBachelor of Technology (BTech), Computer Software Engineering, Bachelor of Technology (BTech), Computer Software Engineering at Uttaranchal University
Github Skills (10)
object-detection10
computer-vision10
pytorch10
faster-rcnn10
deep-learning10
data-augmentation10
python10
ocra9
ocr9
tensorflow4
Programming languages (2)
Github contributions (5)
mindee/doctr
Nov 2021 - Jan 2022
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.
Role in this project:
ML Engineer
ML EngineerContributions:85 reviews, 26 commits, 31 PRs in 2 months
Contributions summary:Siddhant primarily contributed to the development and enhancement of object detection capabilities within the docTR repository, specifically for artefact detection. Their work involved the implementation of a training script, including integrating datasets, defining model architectures (Faster R-CNN), and incorporating photometric and geometric augmentations. The user also developed an inference script and post-processing routines for the artefact detection model, enabling practical usage.
ocr-recognitiontext-documentoptical-character-recognitiontext-recognitioncomputer-vision
cryptic-glitch/AI_text_dect
Dec 2023 - Dec 2023
Contributions:42 pushes, 17 branches in 2 days
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.