Large Language Models (LLMs), Generative AI, Cloud AI services, Prompt Engineering

Large Language Models (LLMs), Pytorch, Docker, Python, Kubernetes, Generative AI, Prompt engineering, Distributed high throughput and low latency architectures, Azure CPU GPU environments, TRL, Transformers, Deepspeed

Python, Deep Learning, Microservices, Machine Learning, LLMs, Agentic AI frameworks, Vector Databases, Model evaluation techniques, AutoGen, CrewAI, RAG architectures, Generative AI, LangGraph, Prompt engineering

Sql, Python, time-series forecasting, Generative AI tooling, R, tree-based models, classical ML modeling, observability monitoring tools