About this role
Develop solutions using LLMs, MCPs, RAG, and agentic orchestration patterns, working with Strands Agents, Skills, Claude models, and Amazon Bedrock. Design multi-agent architectures, implement NER, relation extraction, and entity resolution, and build evaluation and trust-scoring mechanisms for hallucination detection, output consistency, and KPI accuracy.
Skills for this role
LLMsMCPsRAGAgentic orchestration patternsStrands AgentsSkillsClaude modelsAmazon BedrockMulti-agent architecturesNERRelation extractionEntity resolutionAgentic workflowsTool useMCP server implementationStateful agent orchestrationEvaluation and trust-scoring mechanismsHallucination detectionOutput consistencyKPI accuracy