I am a Computer Science undergraduate at Netaji Subhas Institute of Technology, passionate about the intersection of Software Systems and Artificial Intelligence.
My focus is on bridging the gap between high-level AI research and low-level system performance. I enjoy building tools that make AI efficient, accessible, and fast.
🔭 Current Engineering Focus
- Inference Optimization: Compiling and optimizing Large Language Models (LLMs) for local execution using C++ and industry-standard runtimes.
- Generative AI Systems: designing retrieval-augmented architectures (RAG) that combine vector search with autonomous agents.
- Open Source: actively contributing to machine learning infrastructure and documentation.
🛠️ Technical Stack
- Languages: C++, Python, SQL, JavaScript.
- Frameworks: PyTorch, LangChain, OpenVINO, React.
- Infrastructure: Docker, Git, Visual Studio, CMake.
⚡ About Me: I enjoy the challenge of "getting under the hood"—whether that is debugging compilation flags on Windows or implementing custom memory management for inference engines.
📫 Reach me: yugansh5013.s@gmail.com