I am a dedicated software engineer specializing in Machine Learning, Deep Learning and Computer Vision. I thrive on merging cutting-edge algorithms with robust hardware solutions to build innovative products tha 85D7 t address real-world challenges.
Check out my personal page!
-
Machine Learning & Deep Learning:
I design, develop, and optimize advanced ML/DL models to tackle complex problems, ranging from image classification to object detection. My work emphasizes model efficiency, robust performance, and deployment on edge devices. -
Computer Vision:
I create and refine real-time object detection pipelines, enhancing performance with low latency and high accuracy. My projects integrate state-of-the-art computer vision techniques, including utilizing 3D Gaussian Splatting to construct indoor spaces for Xplorer and implementing real-time object detection for product deployment. This work not only supports the company's expansion into new manufacturing domains but has also contributed to award-winning achievements, such as the AI AOI application recognized in the AI Award Best Solution.
- Languages: Python, C/C++, CUDA, Swift
- Frameworks & Libraries: TensorFlow, PyTorch, OpenCV, TensorRT
- MLOps: Tensorboard, MLflow, W&B
- Hardware: NVIDIA GPUs
- Expertise: Algorithm design, optimization, quantization-aware training, latency reduction, and robust system integration
I'm passionate about pushing the boundaries of technology and am eager to work with teams and companies at the forefront of ML, DL, camera systems, and embedded software development. If you're looking for an engineer who combines technical prowess with a creative approach to problem-solving, let's connect!
Feel free to reach out at [s910247@gmail.com] or connect with me through my GitHub profile.