AgentCore Platform Engineer

Join our team as an AgentCore Platform Engineer, where you will build the agent-facing layer of our platform. You will focus on either Agent Runtime & Orchestration or Gateway, Tools & Integrations, and your work will set the standard for other teams. You should have strong AWS fundamentals, experience with agent frameworks, and a passion for creating reusable patterns.

• Concevoir et construire des modèles d'exécution, des stratégies de mémoire, de l'orchestration et des transferts multi-agents, ainsi que des implémentations de référence.
• Transformer les API internes, les fonctions Lambda et les systèmes hérités en outils régis via AgentCore Gateway, y compris le développement du serveur MCP.
• Établir l'authentification et l'autorisation pour les agents et les outils (AgentCore Identity, OAuth, IAM) afin que les agents n'accèdent qu'à ce qu'ils sont autorisés à atteindre.

• We know production experience with Bedrock AgentCore is rare. We care more about strong AWS fundamentals and real hands-on work with agent frameworks than about whether you’ve used AgentCore by name. If that’s you, please apply
• Clean, well-tested code that other engineers will read and reuse
• Clear communication and comfortable teaching patterns to other teams
• Understanding of agent memory, retrieval (RAG) and context management trade-offs
• You have prior experience in consulting
• You care about patterns other people can copy, not just clever one-offs
• Practical experience with LLM tool/function calling and handling model output
• Deep hands-on strength in at least one of the two focus areas, and working knowledge of the other
• You work well inside a client team and enjoy helping other engineers succeed
• You pick up new AWS services quickly and learn by building
• You’ve built agents that actually work, and you know where they tend to break
• Experience designing and consuming REST APIs and OpenAPI specs, and auth patterns such as OAuth 2.0 and OIDC
• Strong AWS fundamentals: IAM, Lambda, API Gateway, containers, DynamoDB/S3, VPC connectivity and Secrets Manager
• You’re honest about what agents can and can’t do today
• Hands-on experience building LLM agents with at least one agent framework (e.g., Strands Agents, LangGraph, LangChain, CrewAI, OpenAI Agents SDK, LlamaIndex)
• Prior experience and connections in the Life Sciences industry is preferred
• 5+ years of software engineering experience, with strong Python (TypeScript is a plus)
• You think about security and access control before anything goes live
• Hands-on experience with Amazon Bedrock AgentCore (Runtime, Memory, Gateway, Identity). A strong plus, but not required
• Experience with multi-agent systems in production, including observability and failure handling
• Experience building or running MCP servers in a real environment
• Experience integrating with enterprise or legacy systems, or with API management platforms (e.g., MuleSoft, Apigee, Kong)
• Experience with LLM evaluation tools and approaches
• Experience in pharma, life sciences or another regulated industry with data access controls