About this role
Design, build, and deploy enterprise-grade GenAI and Agentic AI solutions using LLMs, RAG, tool calling, and multi-agent architectures; develop backend services, document ingestion and vector retrieval pipelines, and deploy/monitor applications using Docker, Kubernetes, CI/CD and cloud platforms.
Skills for this role
PythonGenAIAgentic AILarge Language Models (LLMs)Retrieval-Augmented Generation (RAG)Tool callingAgent orchestrationLangGraphLangChainAutoGenCrewAISemantic KernelLlamaIndexEmbeddingsPrompt EngineeringSemantic SearchVector DatabasesOpenAIAzure OpenAIAWS BedrockAnthropic ClaudeGeminiLlamaMistralOpenSearchPineconeChromaFAISSWeaviateMilvus (vector DB) - note: as listed on source