* 🔭 I’m currently working on high-throughput LLM inference engines and production-grade RAG systems using LangChain, ChromaDB, and serverless architectures.
* 👯 I’m looking to collaborate on open-source GenAI frameworks, MLOps/LLMOps pipelines, and high-performance model optimization tools (vLLM, TensorRT, Triton).
* 🤝 I’m looking for help with scaling distributed GPU clusters and advanced quantization strategies for edge deployments.
* 🌱 I’m currently learning advanced LLM fine-tuning techniques (LoRA/QLoRA), agentic workflows, and real-time audio/speech AI systems.
* 💬 Ask me about Python, PyTorch, XGBoost, Vector Databases, building 6-phase automated ETL pipelines, or deploying AI apps to Hugging Face & Cloud.
* ⚡ Fun fact I transitioned from a Civil Engineering background to building production AI/ML systems and scored a 98.55% accuracy on Kaggle's MNIST challenge!
