A fast-scaling AI startup is building the AI platform companies use to run their business on agents. A customer describes an outcome in plain English, and the platform gets the work done across their tools and systems.
About the role
We're looking for unusually strong engineers, from mid-level to Staff+, to build the product across three areas:
Product: The experiences through which people use the platform across our web and mobile apps, website, onboarding, and everything else our users touch, making powerful agents feel simple, fast, trustworthy, and delightful.
Platform: The backend APIs behind product features; accounts, workspaces, permissions, billing, payments, and analytics; and the connector, authentication, webhook, and automation infrastructure that lets the platform act across a company's tools.
AI Infrastructure: The core machinery that makes the agents capable, reliable, efficient, and scalable, including our agent harness, context management, filesystem, and execution environment, as well as model serving, databases, Kubernetes, networking, and cloud infrastructure.
You may have a clear center of gravity in one of these areas, or your interests and experience may span more than one. You do not need to decide exactly where you fit before applying. We'll work with you to identify where your strengths, interests, and judgment can have the most impact.
These are broad engineering roles, not narrow specializations. You'll follow important problems wherever they lead, from interaction design and client architecture to APIs, data models, agent runtimes, storage, distributed systems, and production infrastructure. We care more about intelligence, first-principles reasoning, and strong computer-science fundamentals than a conventional AI resume, exact stack match, or experience with any particular technology or domain.
What you'll do
Regardless of level, this is a hands-on IC role: everyone personally builds and ships. Your work may center on one of the following areas or span several of them:
Product
Build the user-facing product across web, mobile, and other surfaces.
Invent clear interactions for delegating work to agents, following their progress, handling uncertainty, and using their output.
Own features end to end, from early product thinking through polished production software.
Prototype quickly, learn from customers, and turn the best ideas into durable systems.
Platform
Build backend APIs and services that power the product.
Develop core systems for identity, workspaces, sharing, permissions, billing, payments, and analytics.
Build reliable infrastructure for connectors, authentication, webhooks, automations, and third-party integrations.
Design simple abstractions and data models that can support a fast-changing product.
Own systems in production and improve their correctness, security, reliability, and operational simplicity.
AI Infrastructure
Build the agent harness, including orchestration, tool execution, state, evaluation, and failure recovery.
Develop context-management, filesystem, memory, storage, and sandboxed-execution systems.
Work on model routing and serving, databases, Kubernetes, networking, queues, and cloud infrastructure.
Make long-running agent workloads faster, safer, more reliable, and more cost-efficient.
Turn fast-moving advances in models and agent systems into robust production capabilities.
For all three areas, you'll work across the stack and across role boundaries whenever that is the best way to solve the problem.
Who you are
You're an exceptional problem solver with strong computer-science fundamentals.
You reason from first principles, form clear mental models, and see how parts interact within a larger system.
You've shipped meaningful, high-quality production software and owned it after launch. You can debug a problem wherever it leads.
You care about both clean design and real outcomes, whether that means product craft, performance, correctness, security, reliability, safety, cost, or operational simplicity.
You learn quickly, operate well with ambiguity, and prefer responsibility over process.
You use AI deeply in your own work. We don't require prior professional AI experience, but we do expect you to already be seriously engaged: using current models, probing their limits, following the field closely, and forming your own views about where AI systems are going and how they should work.
- Focus on delivering highly usable products; not necessarily customer-facing.
- Strong computer science fundamentals; CS degree from a top school preferred.
- 3+ years of experience, but open to exceptions based on candidate strength.
- Deep thinkers with solid frameworks for problem-solving.
- Motivated to contribute to a startup environment with high autonomy.
- Preference for candidates with experience in selective companies known for technical rigor.
- Strong track record of progression and impact in previous roles.
- 2-15 years of experience shipping production TypeScript full-stack, with backend/infra ownership from a top CS undergrad program
- Experience at highly selective companies (top Big Tech, well-known startups) with clear progression/promotions or founding experience
- Strong internship experience during undergrad
- TypeScript in production across a Node backend and a React frontend
- Python for sandbox/runtime work
- Hands-on GCP and Docker - owns their own deploys and debugs at the container/Linux level
- Eager to be an IC and write code every day
- BS/BA in Computer Science from a top undergrad; Master's in CS does not substitute
- Dual degree including CS