🚀 AI Engineer | I Help Build High-Performance GenAI & Computer Vision Solutions | PyTorch - TensorFlow - Built 5+ AI Projects | Python Expert | Open to Entry-Level AI & ML Roles

---

🔥 OPEN TO OPPORTUNITIES 🔥

Actively seeking AI Engineer / Computer Vision Engineer roles

🎯 Core Competencies: Deep Learning • Computer Vision • Multimodal AI • Real-Time Systems • Research Implementation

🎯 Tech Stack: Python | PyTorch | Stable Diffusion | CLIP | GANs | Latent Diffusion Models

A unified multimodal AI platform integrating comic generation, image style transfer, text-to-image synthesis, animation, inpainting, and 2D-to-3D reconstruction. Implements cutting-edge deep learning architectures including Stable Diffusion, PersonaGPT, VGG19, AdaIN, and voxel-based 3D modeling.

Key Features:

• ✅ AI-powered comic generation with narrative synthesis
• ✅ Neural style transfer preserving 98% structural similarity
• ✅ CLIP-based text-to-image with 96% semantic accuracy
• ✅ Depth estimation & 3D reconstruction (91% accuracy)
• ✅ Research-backed implementation (2 published papers)

🎯 Tech Stack: Python | YOLOv5 | YOLOR | VGG16 | TensorFlow | OpenCV

Real-time deep learning system for road safety monitoring using state-of-the-art object detection models. Achieves high-accuracy speed breaker detection for autonomous vehicles and driver assistance systems.

Key Achievements:

• ✅ Multi-model ensemble (YOLOv5, YOLOR, VGG16)
• ✅ Real-time processing for ADAS applications
• ✅ Comprehensive dataset creation & annotation
• ✅ Deployment-ready inference pipeline

🎯 Tech Stack: Python | Scikit-Learn | SVM | Random Forest | KNN | Signal Processing

Real-time EMG sensor-based hand gesture recognition system for intuitive human-computer interaction and assistive device control. Implements multiple ML classifiers with feature engineering for robust gesture classification.

Key Features:

• ✅ Real-time EMG signal processing & classification
• ✅ Multi-algorithm comparison (SVM, KNN, RF, Naive Bayes)
• ✅ Virtual mouse controller implementation
• ✅ Feature extraction (MAV, ZCR, RMS, Variance)
• ⭐ 2 GitHub Stars

📖 Perceptive Multimodal Generative AI (PMG-1) Authors: Rithani M., Sidesh Sundar S., Vimal Dharan N., SyamDev R. S. Focus: Comic generation, style transfer, and multimodal content creation

📖 Perceptive Multimodal Generative AI (PMG-2) Authors: Rithani M., Sidesh Sundar S., Vimal Dharan N. Focus: Text-to-image synthesis, animation, and 2D-to-3D reconstruction

■ EMG-Based Hand Gesture Recognition for Assistive Technologies Authors: Vimal Dharan N., [Co-authors TBD] Focus: Real-time EMG signal processing, feature engineering, and ML-based gesture classification for human-computer interaction

AI & Machine Learning
├── Deep Learning (CNNs, RNNs, Transformers, GANs)
├── Computer Vision (Object Detection, Segmentation, Style Transfer)
├── Natural Language Processing (CLIP, GPT-based models)
├── Generative AI (Stable Diffusion, Latent Diffusion Models)
└── 3D Vision (Depth Estimation, Voxel Modeling, Mesh Generation)

Specializations
├── Multimodal AI Systems
├── Real-time Object Detection (YOLO family)
├── Neural Style Transfer (VGG19, AdaIN)
├── Signal Processing (EMG, Time-series)
└── Research & Technical Writing

Development
├── Python (Advanced), C/C++ (Intermediate)
├── PyTorch, TensorFlow, Keras
├── Git, Docker, Linux
└── Jupyter, Google Colab, Weights & Biases

• 🔥 Enhancing PMG-AI with ControlNet and LCM integration
• 🧑‍🔬 Exploring AI Safety and alignment research
• 🎓 Pursuing certifications in Advanced Deep Learning
• 🚀 Building Agentic AI systems with LangChain
• 💡 Contributing to open-source AI projects
• 🔍 Actively seeking AI Engineer / ML Engineer roles (10+ LPA)

• 👨‍🏫 B.Tech in CSE (AI Specialization) - Amrita Vishwa Vidyapeetham
• 📑 2 Research Papers on Multimodal Generative AI
• 🥇 Top Performer in Deep Learning and Computer Vision projects
• ⭐ GitHub Stars: Contributing to open-source AI projects
• 🛠️ Technical Skills: 15+ AI/ML frameworks and tools mastered
• 💡 Innovation: Created unified platform for multimodal generative AI

• 🧠 Agentic AI - Building autonomous AI agents with LangChain & AutoGPT
• 🌐 LLM Fine-tuning - PEFT, LoRA, QLoRA techniques
• ⚙️ MLOps - Docker, Kubernetes, CI/CD for ML models
• 🛡️ AI Safety - Alignment, interpretability, and robustness
• 📊 Advanced Computer Vision - NeRF, Gaussian Splatting, 3D Vision

💖 Thank you for visiting my profile!

---

⭐ If you find my work interesting, consider starring my repositories!