
ML models are not judged only by whether they work or not. We need mathematical metrics to measure how good a model actually is. These metrics help us to compare models, improve predictions and avoid
ML Engineer building LLM applications, RAG systems & open-source AI infrastructure
Machine Learning Engineer and open-source developer focused on NLP, LLM applications, Retrieval-Augmented Generation (RAG), semantic search, and AI infrastructure. I enjoy building developer tools, portable AI systems, and production-ready ML pipelines using Python, FastAPI, FAISS, LangChain, TensorFlow, and PyTorch. Creator of: • RagBucket — portable executable RAG artifacts for Python • LazyTune — fast hyperparameter optimization library • AkBOT — AI portfolio chatbot using RAG Contributor to open-source projects including NumPy and LocalStack.
Markdown supported · ⌘↵ to post
No responses yet.