Tech Lead – Agentic Memory Architecture

We are looking for a Tech Lead specializing in Agentic Memory Architecture to design the memory capabilities of an enterprise AI Agent Platform being built from the ground up.

The role will focus on defining how AI agents store, retrieve, consolidate, and manage context across sessions, enabling both short-term conversational continuity and durable long-term memory while maintaining appropriate isolation, retention, and compliance controls.

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.

• Define the overall agent memory architecture and taxonomy, covering short-term and long-term memory.
• Design and implement memory capabilities using AWS AgentCore Memory, including resource configuration and namespace isolation.
• Define memory extraction strategies for conversation summaries, facts, preferences, and other durable contextual information.
• Design agent memory lifecycle patterns covering memory writes, retrieval, relevance filtering, and retention.
• Establish patterns for multi-session state management and agent personalization.
• Design memory-enabled agents using configuration-driven approaches and managed memory capabilities.
• Define and implement memory consolidation and relevance-scoring strategies.
• Establish observability for agent memory, including memory writes, retrieval effectiveness, and storage growth.
• Define appropriate retention and deletion mechanisms to support privacy and compliance requirements.
• Provide technical leadership and architectural guidance for teams implementing memory-enabled AI agents.
• Evaluate and integrate memory capabilities from frameworks such as LangChain and LangGraph, where appropriate.
• Support semantic memory use cases and integration with vector-based retrieval technologies.

• Agentic memory taxonomy — short-term (session continuity), long-term (durable facts, preferences)

• AWS AgentCore Memory — resource provisioning, namespace isolation per agent, memory strategies

• Memory extraction strategies — Summary (conversation summaries), Semantic (user facts/preferences)

• Agent memory lifecycle — write-on-turn, retrieve-on-turn, relevance filtering, TTL retention

• Memory-enabled agent design — configuration-driven memory without custom infrastructure

• Agent memory observability — tracking memory writes, retrieval effectiveness, storage growth

• 6+ years building AI/ML systems or conversational AI platforms

• Designed memory or context management for LLM agents or chatbots

• Multi-session state management and personalization systems

• Data retention policies and compliance (GDPR user deletion)

• AWS AgentCore Memory hands-on experience

• LangChain/LangGraph memory modules

• Vector databases for semantic memory (Pinecone, Chroma, FAISS)

• Memory consolidation and relevance scoring