About this role
Design and implement end-to-end LLM applications using Python and LangChain, and develop and optimize RAG data pipelines including ingestion, chunking, embedding generation, and vector indexing. Perform model tuning and prompt engineering, deploy LLM applications to cloud platforms, and develop evaluation metrics and frameworks for monitoring LLM output quality.
Skills for this role
PythonLangChainLarge Language Models (LLMs)Retrieval-Augmented Generation (RAG)Generative AIPrompt EngineeringFine-tuningLLM AgentsChainsCustom ToolsVector DatabasesPineconeChromaMilvusEmbedding ModelsData PipelinesData IngestionChunkingVector IndexingAWSAzureGCPDeploymentScalabilityEvaluation Frameworks