Performance Tuning, Api Integration, Tensorflow, Pytorch, Python, LangChain, LLMs, cloud platforms, Monitoring, microservices-based architectures, prompt engineering, model evaluation, MLOps tools, RAG pipelines, AI frameworks

Apis, Cloud deployment, Microservices, MLops, Python, LangChain, orchestration frameworks, embeddings, data pipelines, LLMs, vector databases, AutoGen, LangGraph

Pytorch, Docker, Flask, Python, FastAPI, Kubernetes, AWS Bedrock, Hugging Face Transformers, Qdrant, re-ranking, LLM application development, Pinecone, LangSmith, LangGraph, fine-tuning open-source models, Mistral, Google Vertex AI, RAG pipelines, ChromaDB, Weights Biases, LangChain, LLaMA, vLLM, hybrid search, LoRA, Arize Phoenix, Milvus, QLoRA, LlamaIndex

MLops, Pytorch, Kubernetes, Python, Hugging Face, vLLM Triton, Vector Databases, LLM Gateway, Agentic AI, Self-hosted Models, RAG, LLM Generative AI, LLM Orchestration

Azure Sql, Azure Storage, Agile Scrum, Microservice architecture, Ocr, Azure Functions, Python, Nlp, Restful Apis, Azure DevOps, Event-driven patterns, Responsible AI practices, Monitoring, Configurable systems, Azure API Management, Web interfaces, Structured logging, Orchestration engines, Asynchronous messaging, Observability, Large Language Model APIs

.NET, Sql, Web Apis, Cosmos DB, Devops, Azure Functions, AWS, Nosql, Azure, Docker, Nlp, Git, ML.NET, LLMs, Azure Cognitive Services, Microsoft Semantic Kernel, Azure OpenAI, App Service, CI CD, AI ML models, ASP.NET Core, OpenAI APIs, Generative AI

Cloudformation, Tensorflow, Numpy, Jenkins, Git, Gcp, Pytorch, Pandas, Terraform, Spark, FastAPI, Azure, Python, Kubernetes, AWS, LangChain, scikit-learn, Hugging Face Transformers, MLflow, vLLM, TF Serving, GitHub Actions, TorchServe

Tensorflow, Pytorch, Python, Docker, Azure Machine Learning, Azure DevOps, MLops, Azure OpenAI Service, CI CD pipelines, prompt engineering, generative AI

Tensorflow, AWS, Pytorch, Python, Azure, Gcp, GPTQ, LlamaIndex, ChromaDB, PEFT, vector databases, AWQ, LoRA, model quantization, RAG frameworks, LangChain, Pinecone, FAISS, prompt engineering, LLM architectures