Abhik Sarkar

I am Abhik Sarkar, a machine learning engineer focused on building real-world computer vision systems that actually run at scale. My work lives at the intersection of software engineering, GPU hardware, and production reliability .

I currently lead machine learning at Cloudastructure, where I design end-to-end vision pipelines spanning high-throughput video ingestion, GPU-accelerated decoding, and low-latency inference. My daily toolset includes PyTorch, TensorRT, NumPy, OpenCV, CuPy, PyCUDA, and ONNX Runtime.

Outside of work, I actively seek technical discussions and regularly attend conferences to understand how engineers around the world approach hard problems. I care as much about learning as I do about sharing, and I make a deliberate effort to pass on whatever I know in a form others can actually use.

In my free time, I cook, and I make chocolate bars from raw cacao beans.