About this role
Design, build, and scale AI-powered applications at Lilly using Large Language Models, agentic AI workflows, and Retrieval-Augmented Generation; develop responsive frontends and scalable backend services, integrate AI services with business applications, and deploy cloud-native solutions on AWS using Docker and Kubernetes.
Skills for this role
Large Language ModelsAgentic AIRetrieval-Augmented Generation (RAG)LangGraphLangChainLlamaIndexOpenAIAnthropicBedrockAzure OpenAIVector databasesSemantic searchPythonFastAPIFlaskMicroservices architectureAPI designReactTypeScriptAWSDockerKubernetesCI/CDGitHub ActionsJenkinsGitLabPostgreSQLMySQLSQL ServerNoSQL databases''Prompt Engineering''Model Context Protocol (MCP)''AI observa