Backend Engineer – Memory Integration

We are looking for a Backend Engineer to build and integrate reusable memory capabilities for enterprise AI agents. The role focuses on session and context persistence, memory APIs, isolation and scoping patterns, and Python-based platform components that allow agents to use memory consistently with minimal custom implementation.

Our client is a large global enterprise operating across multiple markets, with a complex technology landscape and a strong focus on digital transformation and innovation. The organization is actively investing in modern cloud, data, and AI capabilities to enable scalable, secure, and highly automated solutions across its business.

The project is focused on building an enterprise-grade AI Agent Platform from the ground up. The platform will provide a standardized foundation for developing, deploying, orchestrating, securing, and observing AI agents across multiple teams and use cases.

The initiative covers the full agent lifecycle and brings together agent orchestration, observability, security, governance, integrations, evaluation, and platform engineering. Engineers joining the project will have an opportunity to influence key architectural and technical decisions and contribute to a new platform rather than maintaining an existing solution.

• Implement agent memory integration patterns, including write-on-turn storage of session events and retrieve-on-turn access to relevant context.
• Integrate with AWS AgentCore Memory APIs for creating, querying, updating, and deleting agent memory.
• Design memory namespaces and isolation patterns, including per-agent separation and per-user scoping.
• Develop reusable Python SDKs and helper libraries that simplify memory integration for agent developers.
• Integrate memory capabilities into standard agent templates, enabling memory through configuration rather than requiring custom application code.
• Implement reliable session management and context persistence across agent interactions.
• Build and maintain integrations with stateful backend services supporting agent memory.
• Ensure memory functionality can be consistently reused across different agents and applications within the platform.

• Agent memory integration — write-on-turn (store session events), retrieve-on-turn (fetch relevant context)

• AWS AgentCore Memory API — create memory, query memory, update memory, delete memory

• Memory namespace design — per-agent isolation, per-user scoping

• Python for agent memory helpers — platform library for memory-enabled agents

• Agent template integration — turn on memory by configuration, no custom code

• 4+ years backend engineering with AI/ML systems

• API integration for stateful services

• Session management and context persistence

• Python SDK development

• AWS AgentCore Memory SDK usage

• LangChain memory integration

• Agent framework development (LangGraph, Crew)

• Conversational AI context handling