AI / ML Engineer & Full Stack Developer

Yougal
Attri

B.Tech in Computer Science (Data Science) from Akal University. I build production-grade machine learning pipelines and full-stack applications — from geospatial segmentation models to cybersecurity web platforms.

Get in touch LinkedIn Resume
GitHub +91 78074 03195
YA

Technical Skills

🤖 AI / ML
PyTorch TensorFlow SAM SegFormer scikit-learn OpenCV FastAPI
🌐 Full Stack
React.js Node.js Express.js MongoDB JWT Auth REST APIs
💻 Languages & Data
Python JavaScript C/C++ NumPy Pandas SQL
🛠️ Tools & Infra
Git Docker Postman Jupyter VSCode

Experience

Full Stack Developer Intern (MERN)

Panacea Infosec Pvt. Ltd. · New Delhi

Jan – Apr 2025
  • Built responsive frontend modules for a cybersecurity audit web app using React.js, HTML, and CSS.
  • Implemented RESTful APIs with Node.js & Express.js; integrated JWT-based auth with role-based access control.
  • Managed MongoDB, Git version control, and Postman API testing in an agile team.

AI / ML Intern

Panacea Infosec Pvt. Ltd. · New Delhi

Jun – Dec 2024
  • Fine-tuned SAM and SegFormer on complex geospatial datasets — up to 75% accuracy in variable conditions.
  • Engineered scalable training and inference pipelines using PyTorch, TensorFlow, and FastAPI.
  • Optimised model robustness through rigorous experimentation in real-world remote sensing scenarios.

Data Science Intern

Sabudh Foundation · Mohali, Chandigarh

Jan – Jun 2024
  • Designed supervised and unsupervised ML models for social impact datasets.
  • Built a classification pipeline with 95% accuracy to automate data categorisation.
  • Improved analysis turnaround by 30% using Pandas and scikit-learn workflows.

Key Projects

Geospatial Segmentation with SAM

Fine-tuned Meta's Segment Anything Model for land-use classification and geospatial boundary detection via transfer learning and data augmentation.

▲ 70% over baseline · PyTorch · SAM

Semantic Segmentation · SegFormer

Multi-class segmentation pipeline using transformer architecture for remote sensing, with custom loss functions for imbalanced classes.

75% accuracy · SegFormer · TensorFlow

Food Product Classification System

End-to-end ML pipeline with custom web scraping for data acquisition, processed with Pandas & scikit-learn for market intelligence at scale.

95% accuracy · Python · scikit-learn

Contact

✦ Available now

Let's build
something great.

Open to AI/ML and full-stack roles. Fast replies guaranteed.

Email Me LinkedIn Call Me