AI/ML Engineer specializing in computer vision, reinforcement learning, and evolutionary algorithms. I focus on developing robust machine learning solutions and contributing to the open-source community through practical implementations and technical research.

Research Interests: Neural Architecture Search, Distributed Training Systems, Edge AI Optimization

• Military Vehicle Object Detection - Production-ready object detection pipeline with custom dataset curation and model optimization
• ONNX Model Object Detection with C++ - Cross-platform C++ inference engine achieving 60+ FPS on edge devices
• Breast Tissue Cropper Tools - Medical imaging pipeline with automated quality assessment and DICOM compatibility

• Project Mechopter - Multi-agent quadcopter control system with distributed training architecture
• PPO Pong Agent - Advanced policy optimization with custom reward shaping and hyperparameter analysis
• Snake Game RL Solution - Comparative study of Actor-Critic vs PPO with performance benchmarking

• ESRGAN Super Resolution - Enhanced GAN architecture with perceptual loss optimization for 4x upscaling

• Particle Swarm Optimization - Comprehensive PSO framework with adaptive parameters and convergence analysis
• Genetic Algorithm Game Solutions - Evolutionary strategies applied to game AI with population dynamics visualization

• C++ Data Structures - High-performance implementations with memory profiling and complexity analysis
• Video Processing Pipeline - Scalable video analysis toolkit with batch processing capabilities
• Colab Session Manager - Automated resource management for distributed training workflows

Selected technical articles exploring advanced AI concepts and implementations:

Spike Neural Networks: Neuromorphic Computing Fundamentals
Comprehensive analysis of spiking neural networks, temporal coding, and hardware acceleration strategies for neuromorphic systems.

Particle Swarm Optimization: Theory and Applications
Mathematical foundations of PSO with convergence proofs and multi-objective optimization case studies.

Signal Processing Fundamentals for Machine Learning
Bridge between classical signal processing and modern deep learning architectures.

Core Competencies

• Machine Learning: Deep Learning, Computer Vision, Reinforcement Learning, Generative Models
• Optimization: Evolutionary Algorithms, Hyperparameter Tuning, Neural Architecture Search
• Systems: Distributed Training, Model Deployment, Edge Computing

Technology Stack

• Languages: Python, C++, CUDA, JavaScript
• Frameworks: TensorFlow, PyTorch, JAX, OpenCV, ONNX Runtime
• Infrastructure: Docker, Kubernetes, MLflow, Weights & Biases
• Hardware: NVIDIA GPUs, Intel Neural Compute Stick, Jetson platforms

Current Focus Areas

• Efficient neural network architectures for resource-constrained environments
• Multi-agent reinforcement learning systems
• Automated machine learning pipeline development