About this role
Architect and build custom AI infrastructure and hardware solutions, optimizing performance, power consumption, cost and scalability. Design, integrate and operationalize enterprise-grade LLM, GenAI and agentic AI components on AWS including RAG, agents, retrieval pipelines and safety/control mechanisms.
Skills for this role
Large Language Models (LLMs)Amazon Web Services (AWS)Cloud-native engineeringPythonAPIsDistributed systemsCI/CDAutomated testingObservabilitySecure SDLCAmazon BedrockBedrock AgentsAgentCoreKnowledge BasesGuardrailsAWS LambdaAPI GatewayStep FunctionsOpenSearch ServerlessOpenSearch Vector EngineAmazon SageMakerIAMCloudWatchCloudTrailVPCKMSS3RAGFunction callingAgent orchestration