Software Development Manager, AgentCore Memory

Want to build the memory layer that gives AI agents the ability to learn, remember, and get smarter over time? Come lead engineers on the team building AgentCore Memory, the managed service that lets developers give their AI agents persistent, secure, and intelligent long-term and short-term memory at scale.

AgentCore Memory is at the heart of the agentic AI revolution. Every meaningful agent experience that remembers customer preferences, recalls past conversations, and improves with every interaction, depends on a memory system that is fast, durable, and secure. As a Software Development Manager for the team, you will own a mission-critical service that thousands of builders rely on to bring stateful, context-aware AI agents to life.

In this role, you will lead and grow a team of talented engineers building globally distributed, high-throughput services that span a control plane, a data plane, and real-time ingestion pipelines. You will

help drive the technical direction and roadmap for a system that blends large-scale distributed systems with cutting-edge generative AI, using Amazon Bedrock to power memory extraction and consolidation. You will be accountable for operational excellence across multiple AWS regions, meeting demanding availability, latency, and security bars for a service customers depend on every day. Along the way, you will partner closely with product, science, and cross-functional engineering teams to define what agent memory should be, while coaching and developing engineers, hiring top talent, and cultivating an inclusive, high-performing team culture.

Key job responsibilities

• Lead, coach, and grow a team of software development engineers, owning hiring, performance management, and career development.
• Own the delivery of a globally distributed, high-throughput service spanning control plane, data plane, and real-time ingestion pipelines, from design through deployment and operations.
• Partner with product managers, applied scientists, and cross-functional engineering teams to define the roadmap and translate customer needs into technical plans and prioritized deliverables.
• Drive operational excellence across multiple AWS regions, holding the team accountable for availability, latency, security, and leading on-call and incident response practices.
• Set and uphold a high bar for engineering quality through design reviews, code reviews, testing strategy, and sound architectural decisions.
• Manage dependencies and communicate status, risks, and trade-offs to stakeholders and senior leadership.
• Foster an inclusive, collaborative team culture where engineers do their best work.