System Architect, New Products

You’ll create core building blocks for AI product concepts that the team can dogfood and build on. You’ll shape a reference architecture around models, live context, memory, tools, agent harnesses, and durable execution, making crisp calls about what belongs in each layer. You’ll decide which components should become general platform primitives that other teams can adopt.

• Build shared platform primitives for agentic systems development, such as memory, context management, tools, and background execution.
• Create infrastructure for prototyping, training, and evaluating models, with reusable environments and developer tooling.
• Develop systems for triggers and context capture across devices, surfaces, and modalities.
• Design harnesses and primitives for coordination and execution handoff between models.
• Make these systems reliable and production-ready through observability, recovery, security, and latency and cost controls.