Member of Technical Staff - Agent Systems

Building the autonomous company

Human Intuition is building the autonomous company. Businesses run on accumulated judgment: how to interpret a situation, choose an action, and learn from its consequences. Much of that knowledge lives in people, even when the decisions they make leave traces in software.

We are working to make that judgment learnable. A business has defined systems, tools, permissions, histories, and objectives. Those boundaries create an opportunity to build agents that learn from how work is done, act within clear constraints, and improve through feedback. Our ambition is to turn the knowledge inside institutions into software that compounds.

The role

Build the systems that let an agent carry a task through to a trustworthy outcome. You will own the runtime between models and business software: execution state, tools, permissions, memory, and recovery. These systems need to make agents useful while keeping their actions understandable and controllable.

What you’ll do

• Build durable execution for workflows that involve many steps, external services, and interruptions.

• Design tool interfaces and integrations with clear contracts, scoped permissions, and useful error reporting.

• Implement checkpointing, retries, cancellation, idempotency, and recovery without silently duplicating actions.

• Develop context and memory systems that preserve useful information and its provenance across tasks.

• Make traces inspectable and replayable so researchers and operators can understand decisions and diagnose failures.

• Connect production experience to evaluation and learning systems, and turn research advances into dependable capabilities.

What you’ll bring

• Strong software engineering skills and experience operating backend or distributed systems.

• Fluency in Python or TypeScript and comfort working across service boundaries.

• Practical experience with agents, workflow engines, or other asynchronous systems.

• Good judgment about state, access control, failure handling, and operational reliability.

• The ability to own a problem from design through deployment and maintenance.

Useful experience

Tool-using agents, durable workflow engines, event-driven systems, browser automation, business software integrations, or tracing and observability.

What success looks like

Agents can complete useful work, recover from expected failures, and provide a clear record of what happened and why.

Apply

Show us something you have built, investigated, or improved, and tell us what you learned. That might be a product, a research result, an open-source contribution, or work you can describe without disclosing confidential information. We welcome strong evidence of ability from a range of backgrounds.