IMPLEMENTATION AND OPTIMIZATION OF GPT 2
Summary
Self Deep Learning Project
Work
Document Intelligence Lab | Prof. Santanu Choudhary | Dept. of CSE
|UNDERGRADUATE STUDENT RESEARCHER
Summary
Extracted key information from document images for visual question answering. Experimented with various transformer-based architectures for scene and text understanding like ViBERT, VILBERT, Chargrid, etc. Performed multi-modal learning for VQA (visual question answering) using layout aware scene text transformers.
Novus Hi-Tech Robotics Systems Ltd.
|GRADUATE ENGINEER TRAINEE
Summary
Developing Al-driven AMRs (Autonomous Mobile Robots), L2 Autonomous vehicle for reducing human intervention in shop floors, warehouses, and manufacturing plants. Working on deep learning architectures for V-SLAM, structure from motion, scene reconstruction, and monocular depth estimation. Worked on multiple sensor fusion (camera, lidar, GPS & IMU) for mapping and localization of autonomous vehicles, based on autoware. Finetuned YOLOv8 model on real world data captured from Intet RealSense Depth Camera, for robust pallet detection. Implemented detection and pose estimation from detected bounding boxes using docker container on Nvidia Jetson Nano. Performed multi-view object detection by minimizing epipolar error using Hungarian matching.
Education
NEHRU WORLD SCHOOL
CLASS 12
CBSE
Grade: 95.3%
NEHRU WORLD SCHOOL
CLASS 10
ICSE
Grade: 90.17%
IIT JODHPUR
→
B.TECH
MECHANICAL ENGINEERING
Grade: 7.44/10
Awards
Student Distinguished Contributions Award Winner
Awarded By
IIT Jodhpur
Student Distinguished Services Award Winner
Awarded By
IIT Jodhpur
Represented IIT Jodhpur and Bagged 8th position in InterIIT Tech Meet.
Awarded By
IIT Jodhpur
Skills
PROGRAMMING
C++, C, Python, Simulink, R, Shell, Matlab, Java.
ML/DL TECHNOLOGIES
PyTorch, PyTorch Lightning, TensorFlow, ONNX, TensorRT, OpenCV, ROS1/ROS2, Open3D, Hugging-face, Ollama, SQL, Docker, Git, Scikit-Learn, Rust, SHAP, Xgboost, Lime, EDA, Tableau, Matplotlib.
MLOPS/AI ENGINEERING
AI/MLOps - AWS/Azure/GCP, Model Deployment (Docker & Kubernetes), Weights & Biases (W&B), DVC (Data Version Control), CI/CD for ML (GitHub Actions, GitLab CI), Linux shell utilities, Slurm HPC, RAG, Data Science.
Projects
RAG PIPELINE FOR PDF QUESTION ANSWERING
Summary
Self Deep Learning Project
FINGERPRINT GENERATION USING DIFFUSION MODELS
Summary
Course Project (Advanced ML) | Dr. Mayank Vatsa