We're building an AI-powered desktop application that fundamentally changes how knowledge workers manage their digital workload. Think of it as an intelligent companion that sits alongside you on your laptop - connected to your messages, calendar, and files - understanding your work context and helping you stay on top of everything without the cognitive overhead.
As an SDE-2 on this team, you'll work at the intersection of AI/ML systems and desktop application development. You'll build the infrastructure that lets AI agents operate safely and reliably on a user's machine - from real-time event processing and multi-agent orchestration to local knowledge graphs that evolve as users interact with the system. The problems you'll solve aren't typical CRUD - they involve designing novel architectures for long-running agentic sessions, managing context windows across complex task hierarchies, and building trust through transparent, permission-scoped automation.
This is a 0-to-1 product. You'll ship features end-to-end, influence architecture decisions, and see your work in the hands of users quickly. If you've ever wanted to build software that feels like it genuinely understands and helps people - not just another chatbot, but a proactive partner - this is that opportunity.
Key job responsibilities
* Design and implement core systems for the desktop application's agentic runtime - including task scheduling, agent lifecycle management, and inter-process communication between parallel AI agents
* Build and evolve a local knowledge graph that captures relationships between people, projects, and topics from the user's work environment, enabling contextual and personalized assistance
* Develop integrations with external services (email, messaging, calendar, file storage) using standardized protocols, with a focus on security, permissions, and graceful failure handling
* Own the memory and context management layer - solving hard problems around what information to retain, how to retrieve it efficiently, and how to keep long-running sessions coherent within token constraints
* Contribute to the cross-platform desktop experience (macOS and Windows), ensuring performance and reliability across environments
* Write production code in Python and TypeScript/JavaScript, with an emphasis on clean abstractions that other engineers can build upon
* Participate in on-call rotations, operational reviews, and architecture discussions that shape the product's direction
About the team
We're a small, high-ownership team building an AI-native desktop product from the ground up. Our philosophy is simple: we use what we build. Every day, the team relies on our own product to manage tasks, triage notifications, draft documents, and stay organized - if something doesn't work for us, we fix it before it ships to anyone else.
The team spans applied science and engineering, and we operate more like a startup than a large org. You'll work closely with scientists on memory systems and retrieval, with frontend engineers on the desktop experience, and directly with customers who use the product daily. We value end-to-end ownership, strong opinions loosely held, and shipping delightful experiences over shipping features.
We believe trust is earned through safety - our architecture is designed with least-privilege principles from the ground up, giving users full transparency and control over what the AI can see and do. If you care about building AI systems that are genuinely useful and responsible, you'll fit right in.
Diverse Experiences
AWS values diverse experiences. Even if you do not meet all of the preferred qualifications and skills listed in the job description, we encourage candidates to apply. If your career is just starting, hasn't followed a traditional path, or includes alternative experiences, don't let it stop you from applying.
BASIC QUALIFICATIONS
- 3+ years of non-internship professional software development experience
- 2+ years of non-internship design or architecture (design patterns, reliability and scaling) of new and existing systems experience
- Experience programming with at least one software programming language
PREFERRED QUALIFICATIONS
- 3+ 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
The base salary range for this position is listed below. Your Amazon package will include sign-on payments and restricted stock units (RSUs). Final compensation will be determined based on factors including experience, qualifications, and location. Amazon also offers comprehensive benefits including health insurance (medical, dental, vision, prescription, Basic Life & AD&D insurance and option for Supplemental life plans, EAP, Mental Health Support, Medical Advice Line, Flexible Spending Accounts, Adoption and Surrogacy Reimbursement coverage), 401(k) matching, paid time off, and parental leave. Learn more about our benefits at https://amazon.jobs/en/benefits.
USA, WA, Seattle - 143,700.00 - 194,400.00 USD annually
