AgentCore Platform Engineer

Appnovation Technologies•Austin, TX

12d

About The Position

Appnovation is seeking AgentCore Platform Engineers to develop the agent-facing layer of their platform. This role involves building how agents operate, retain memory, collaborate, and securely access existing business systems. Engineers will focus on one of two key areas: Agent Runtime & Orchestration, or Gateway, Tools & Integrations, while collaborating closely across both. The work produced will serve as a template for other teams, emphasizing the importance of quality, clarity, and speed. While direct experience with Bedrock AgentCore is rare, strong AWS fundamentals and hands-on experience with agent frameworks are highly valued.

Requirements

5+ years of software engineering experience.
Strong Python skills (TypeScript is a plus).
Hands-on experience building LLM agents with at least one agent framework (e.g., Strands Agents, LangGraph, LangChain, CrewAI, OpenAI Agents SDK, LlamaIndex).
Practical experience with LLM tool/function calling and handling model output.
Strong AWS fundamentals: IAM, Lambda, API Gateway, containers, DynamoDB/S3, VPC connectivity, and Secrets Manager.
Experience designing and consuming REST APIs and OpenAPI specs.
Experience with authentication patterns such as OAuth 2.0 and OIDC.
Understanding of agent memory, retrieval (RAG), and context management trade-offs.
Deep hands-on strength in at least one of the two focus areas (Agent Runtime & Orchestration, or Gateway, Tools & Integrations) and working knowledge of the other.
Ability to write clean, well-tested code that is reusable by other engineers.
Clear communication skills and comfort teaching patterns to other teams.
Ability to work well within a client team and help other engineers succeed.

Nice To Haves

Hands-on experience with Amazon Bedrock AgentCore (Runtime, Memory, Gateway, Identity).
Experience building or running MCP servers in a real environment.
Experience with multi-agent systems in production, including observability and failure handling.
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.
Prior experience in consulting.
Prior experience and connections in the Life Sciences industry.

Responsibilities

Define how agents are structured, packaged, and run on AgentCore Runtime, including sessions, state, error handling, and timeouts.
Design short-term and long-term memory patterns using AgentCore Memory and guide teams on their usage.
Build patterns for agent planning, tool use, supervisor/worker setups, and handoffs between agents, including clear boundaries and fallbacks.
Expose internal REST APIs, Lambda functions, and legacy services as agent tools through AgentCore Gateway, utilizing OpenAPI specs and Lambda targets.
Design and build Model Context Protocol (MCP) servers for custom integrations, ensuring clean tool definitions and schemas.
Configure authentication and authorization for agents and tools (AgentCore Identity, OAuth, IAM) to restrict agent access.
Collaborate with system owners to securely wrap older or on-premises systems, managing rate limits, data mapping, and error cases.
Develop production-quality reference agents, starter kits, and a repeatable process for adding, versioning, and reviewing tools.
Implement evaluation, Bedrock Guardrails, contract tests, and safety checks to ensure predictable agent and tool behavior before deployment.
Conduct walkthroughs, create documentation, and support teams onboarding to the platform.