Cuda, Docker, FastAPI, Azure, Python, AWS, LangChain, Anthropic APIs, vector databases, Pinecone, LLM fine-tuning, FAISS, NVIDIA GPU toolkits

CDK, Typescript, FastAPI, Python, Terraform, Docker, Flask, OpenAI, LlamaIndex, Google, Azure OpenAI, LangChain, AWS Bedrock, Anthropic

Nlp, Data structures, Deep Learning, Prompt Engineering techniques, Semantic search techniques, Embedding models, Infrastructure setup, AI model inferencing, Parallel Processing, CUDA architecture, Transformer architectures

Distributed Systems, Python, multimodal systems, vector databases, Pinecone, custom retrieval layers, Swarm, Chroma, transformer architectures, RLHF, LangChain, CrewAI, AI safety, agent frameworks, AutoGen, LLM fine-tuning, LoRA, MLOps tooling, generative AI models, Milvus, OpenAI, Weaviate, QLoRA, LlamaIndex, red-teaming

data wrangling , Cloud Infrastructure, Containers, Python, vector search systems, LLMs, model training, RAG-based systems, CI CD, document knowledge bases, NLP tasks, traditional ML models, feature extraction, large language models, LlamaIndex

Pytorch, Python, PEFT, LLMs, diffusion pipelines, vector databases, real-time streaming generation, ComfyUI, LoRA, RAG, quantization, Stable Diffusion