Tensorflow, Machine Learning, Pytorch, Python, Sql, Api Development, Data Preprocessing, Model Deployment, NLP Techniques, Transformers

Mapreduce, Tensorflow, Numpy, Pytorch, Docker, XGBoost, AWS, Hadoop, Sql, Pig, Pandas, Hive, Gcp, Spark, Python Programming, Azure, Kubernetes, scikit-learn, Hugging Face Transformers, LLM prompt engineering, vector embeddings, RAG pipelines, semantic search, OpenAI API, knowledge retrieval

Node.js, Typescript, Neo4j, Python, LangChain, CrewAI, Playwright, pgvector, Pinecone, AutoGen, LangGraph, Weaviate

S3, Lambda, Docker, Sqs, Sns, Python, Kubernetes, AWS, LLM evaluation and observability tooling, LangGraph, ETL optimization, Agentic AI LLM applications, RAG architectures

Docker, Monitoring Tools, Azure, Kubernetes, Google Cloud, AWS, Machine Learning Operations, model deployment strategies, compliance and security standards in AI operations

Tensorflow, Linux, Rest Apis, Pytorch, Git, FastAPI, Python, Kubernetes, Docker, Generative AI, vLLM, Prompt Engineering, Llama, Fine-Tuning LLMs, LangChain, Pinecone, Embeddings, DeepSeek, CI CD pipelines, Mistral, Ollama, LangGraph, Milvus, ChromaDB, Scikit-learn, Retrieval-Augmented Generation RAG, Hugging Face Transformers, Vector Databases, Qwen, FAISS

Distributed Computing, Pytorch, Docker, Python, Cuda, MLops, Kubernetes, Hugging Face Transformers, model parallelism, speculative decoding, SGLang, inference runtimes, GPU memory management, performance benchmarking, quantization, continuous batching, KV-cache optimization, TensorRT-LLM, LLMOps, vLLM, LLM GenAI model inference optimization, NCCL, Transformer architectures, GPU computing