AgentCore Platform Engineer

Job summary

The AgentCore Platform Engineer role is centered on developing the agent-facing layer of the platform, enabling agents to interact seamlessly with internal systems. Responsibilities include defining runtime patterns, designing memory strategies, and developing Model Context Protocol (MCP) servers, with a strong focus on AWS fundamentals and agent frameworks like Strands Agents and LangChain.

Qualifications

• 5+ years of software engineering experience
• strong Python (TypeScript is a plus)
• Hands-on experience building LLM agents with at least one agent framework
• Practical experience with LLM tool/function calling and handling model output
• Strong AWS fundamentals
• Experience designing and consuming REST APIs and OpenAPI specs
• Understanding of agent memory, retrieval (RAG) and context management trade-offs
• Deep hands-on strength in at least one of the two focus areas
• Clean, well-tested code that other engineers will read and reuse
• Clear communication and comfortable teaching patterns to other teams

Responsibilities

• Define how agents are structured, packaged and run on AgentCore Runtime
• Design short-term and long-term memory patterns using AgentCore Memory
• Build patterns for planning, tool use, supervisor/worker setups and handoffs between agents
• Expose internal REST APIs, Lambda functions and legacy services as agent tools through AgentCore Gateway
• Design and build Model Context Protocol (MCP) servers for systems that need custom integration
• Set up authentication and authorization for agents and tools
• Work with system owners to wrap older or on-premises systems safely
• Build production-quality reference agents, starter kits and a repeatable process for adding, versioning and reviewing tools
• Build in evaluation, Bedrock Guardrails, contract tests and safety checks
• Run walkthroughs, write docs and support the teams onboarding to the platform

Skills

Relocation