About Sycamore

Sycamore is building the trusted agent operating system for the enterprise. Our platform helps companies build, deploy, and orchestrate agentic apps that take on real operational work, with the security and control large organizations need.

We are a small, engineering-led team working directly with Fortune 500 enterprises. We have raised $65M from Coatue and Lightspeed, along with other investors and industry leaders.

Where you could focus

Core AI owns the horizontal runtime, intelligence, and improvement capabilities that Product and Infrastructure both depend on, along with the Sycamore Forge experiences that make them usable. Engineers here own end-to-end slices, from cloud service and API design through the React interface. The team covers four related areas, and you do not have to pick one to apply. Tell us what you have built and we will work out the fit together.

The agent runtime. Multi-turn sessions, model routing, tool execution, memory, durable workflows, and the APIs that expose them. The hard part is correctness across long horizons: surviving retries, provider interruptions, partial failure, and context growth without losing the thread.

Harnesses and environments. An agent that writes and runs code needs somewhere to do it. That environment has to start fast, isolate genuinely untrusted execution, reach only the services it legitimately needs, and carry credentials it can use but never read. The same area owns the verification layer that decides whether what an agent produced actually works rather than only appears to.

Evaluation. Agent quality is genuinely hard to measure. A change that looks better on a handful of examples often is not, and a judge model can be confidently wrong in the same direction as the system it grades. This is where the offline suites, replay corpora, and statistical discipline that gate a release come from.

Self-improving systems. Every agent run produces evidence, and almost all of it is currently thrown away. This area turns it into improvement: structured trajectories at fleet scale, failure clusters surfaced from production rather than guessed at, and proposed changes that are versioned, measured, staged, and reversible.

What you will do

Develop the learning data plane around agents: structured trajectories, feedback and outcome signals, offline datasets, lineage, privacy controls, and reliable links between an agent version and its behavior.

Create evaluation systems for task completion, tool use, long-horizon behavior, safety, latency, and cost, and own the credibility of the numbers they produce.

Design experiment and versioning systems for comparing changes through replay, shadow traffic, canaries, or controlled rollouts, with clear promotion and rollback criteria.

Build durable orchestration for long-running tasks, checkpoints, approvals, handoffs, and human-in-the-loop interactions, with typed tool interfaces, protocol-based execution, and memory retrieval that enforces tenant, user, and project visibility boundaries.

Own the execution environments agents run in, including isolation, startup performance, resource limits, and cost, and the policy layer that gates self-modification so a proposed change is staged and tested rather than applied silently.

Publish reliable APIs, event-driven interfaces, and reusable libraries that work across agent categories and enterprise deployments.

The environment you will work in

Our current Core AI environment includes Python cloud services; React and TypeScript product surfaces in Sycamore Forge; asynchronous and streaming systems; typed APIs and data models; relational and vector data; durable workflows; protocol-based tool execution; multiple model providers; and cloud-native deployment.

We use coding agents, automated tests, traces, evaluations, browser automation, offline replay, cost and latency signals, and production feedback as part of everyday engineering. We are building toward a governed collect, learn, evaluate, and apply loop rather than a single monolithic training system.