Creating solutions that drive real impact.

I'm drawn to the challenge of deploying machine learning models on resource-constrained devices. Training a neural network on a GPU cluster and then making it run efficiently on a microcontroller with 256KB of memory - that's the kind of problem I find compelling. My focus is Embedded AI and Hardware-Software Co-design, learning how to bridge ARM Cortex-M and RISC-V architectures with modern inference engines.

class EmbeddedAI_Engineer {
    public:
        vector<string> interests = {
            "TinyML Applications", "Model Compression", 
            "AI Hardware Accelerators", "Edge Intelligence"
        };
        string passion = "Transforming power engineering & healthcare with AI";
        bool always_learning = true;
};

🔬 Research Focus: Diving deep into TinyML - figuring out how to build efficient inference engines using low-level C++ optimization and quantization techniques. I'm also exploring the exciting world of AI hardware accelerators and what's possible when we push the boundaries of edge computing.

💡 What Drives Me: I love the idea of creating technology that genuinely helps people - whether it's making power grids smarter, healthcare more accessible, or advancing research capabilities. There's nothing quite like the thrill of solving a problem that seemed impossible at first!

Embedded_AI:
  - TinyML Applications
  - Model Compression
  - Quantization Techniques
  - Real-time Inference

Hardware_Acceleration:
  - AI Hardware Accelerators
  - ARM Cortex-M Optimization
  - RISC-V Implementation
  - Low-power Computing

Applications:
  - Power Engineering
  - Healthcare IoT
  - Smart Agriculture
  - Industrial Automation