Senior Software Engineer, AWS Applied AI Solutions

About the role

As part of the AWS Applied AI Solutions organization, we have a vision to provide business applications, leveraging Amazon’s unique experience and expertise, that are used by millions of companies worldwide to manage day-to-day operations. We will accomplish this by accelerating our customers’ businesses through delivery of intuitive and differentiated technology solutions that solve enduring business challenges. We blend vision with curiosity and Amazon’s real-world experience to build opinionated, turnkey solutions. Where customers prefer to buy over build, we become their trusted partner with solutions that are no-brainers to buy and easy to use.

On Agentic WorkSpaces, our vision is to enable AI agents to work the way humans do: with access to real applications, real interfaces, and real computing environments. For enterprises to trust autonomous agents with their essential business applications, they need to see what agents did, control what agents can do, and prove both to auditors. Our team builds the systems that make this possible. We record every agent desktop action as a reviewable visual audit trail, enforce policy on every tool call before it executes, pause agents for human approval on sensitive actions, and package the evidence for compliance frameworks.

We are seeking an exceptional Senior SDE to own the identity architecture at the foundation of this system. When an agent acts inside a user's desktop session, it inherits that user's identity. Every downstream system then attributes the agent's actions to the human. Solving this means deciding how agent identity is established, propagated across protocol and service boundaries, and preserved through to policy enforcement and audit. These decisions determine whether the rest of the governance stack — attribution, enforcement, approval, evidence — can be trusted at all. You will make foundational architectural calls, write code, mentor the engineers around you, and drive consensus with partner teams whose identity models were built for humans. This is a high-visibility, high-ownership role on a small team solving problems with no established playbook.

Responsibilities

• Own the end-to-end identity architecture for agent governance: how agent identity is established, propagated, and preserved across desktop sessions, protocol boundaries, and downstream services
• Design attribution and audit systems that distinguish agent actions from human actions within the same session, at the infrastructure level where agents cannot tamper with the record
• Own policy enforcement architecture, including authorization models that evaluate agent actions before they execute
• Evaluate build-vs-leverage decisions across identity and authorization primitives, including assessments of existing internal and external components for reuse
• Drive technical consensus with partner teams whose identity and permission models predate autonomous agents
• Mentor and develop junior and mid-level engineers through code reviews and design reviews
• Communicate architectural decisions and tradeoffs to senior leadership and non-technical stakeholders

About the team

We're a small team building two greenfield projects within Agentic WorkSpaces. We're moving fast enough that our team name is still taking shape — but our engineering culture is well established.

Basic qualifications

• 5+ years of non-internship professional software development experience
• 5+ years of programming with at least one software programming language experience
• 5+ years of leading design or architecture (design patterns, reliability and scaling) of new and existing systems experience
• Experience as a mentor, tech lead or leading an engineering team

Preferred qualifications

• 5+ years of full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations experience
• Bachelor's degree in computer science or equivalent