Agent Orchestration Engineer

The platform engineer of the agent stack. Cares about queues, retries, idempotency, replay, and the boring infrastructure that makes a flaky LLM call into a reliable system.

Indicative comp$190K – $280K base (US, senior/staff)

Ranges are indicative US base salary at senior level. Actual offers depend on company stage, equity, and candidate strength.

What this role actually owns

Stand up the orchestration substrate the rest of the agent team builds on.
Ensure every agent run is replayable, observable, and bounded in cost.
Implement retry, backoff, and provider failover policies.
Build the dashboards and traces the on-call team uses at 2 AM.
Tune throughput against per-tenant limits and provider rate ceilings.

What we screen for

6+ years backend, with deep experience in at least one workflow engine.
Has run a queue-backed system at scale — can explain why a job got stuck and how they fixed it.
Comfortable instrumenting LLM calls with traces and budgets.
Can talk about idempotency design at the API and DB layer.
Bonus: contributed to Temporal, Inngest, or similar in OSS.

Sample job description

A starting point you can paste into your ATS and adjust. The exact wording matters less than the rubric — the bullets above are what we'll calibrate against during search.

Agent Orchestration Engineer

Owns the runtime — how multi-step agent runs stay reliable, observable, and cheap under real traffic.

You'll own:

Stand up the orchestration substrate the rest of the agent team builds on.
Ensure every agent run is replayable, observable, and bounded in cost.
Implement retry, backoff, and provider failover policies.
Build the dashboards and traces the on-call team uses at 2 AM.

We're looking for:

6+ years backend, with deep experience in at least one workflow engine.
Has run a queue-backed system at scale — can explain why a job got stuck and how they fixed it.
Comfortable instrumenting LLM calls with traces and budgets.
Can talk about idempotency design at the API and DB layer.
Bonus: contributed to Temporal, Inngest, or similar in OSS.