Staff AI Engineer - Agent Architecture & Behavior

Artisan, San Francisco

What you will do

Agent architecture and behavior. Design and implement agent execution loops, planning strategies, tool interfaces, and verification. Turn ambiguous technical requirements into clear system boundaries and working code.
Multi-agent systems. Build delegation, coordination, context sharing, and result synthesis. Handle concurrent work, conflicting updates, cancellation, and stale results. Establish when a multi-agent approach improves on a simpler baseline.
Reliable execution. Make complex, stateful workflows resilient to interruptions and partial failures. Build checkpoints, recovery strategies, and appropriate human intervention into the architecture.

Artisan, San Francisco

$250K–$325K

a year

This base pay is above the median for staff ML and AI engineering jobs in the Bay Area.

We compare the middle of each posted range. This is base pay as posted. The group does not include this job.

Location: San Francisco
Work type: Onsite
Level: Staff
Skills in the job text: Python
TypeScript
Posted: Sep 13, 2026
Last check: 2 days ago
Job type: ML / AI engineering, Inference & ML systems
Visa sponsorship: The job text says that the company can sponsor a visa. Confirm this with the company.

The Artisan site opens in a new tab.

Funding records can have errors and can be missing. The company page has the links.

No one has reported an interview at Artisan yet. Did you interview there? Add the questions.

Compare your résumé with this job. See where you match, what is missing and which lines to change.

Agent architecture and behavior. Design and implement agent execution loops, planning strategies, tool interfaces, and verification. Turn ambiguous technical requirements into clear system boundaries and working code.
Multi-agent systems. Build delegation, coordination, context sharing, and result synthesis. Handle concurrent work, conflicting updates, cancellation, and stale results. Establish when a multi-agent approach improves on a simpler baseline.
Reliable execution. Make complex, stateful workflows resilient to interruptions and partial failures. Build checkpoints, recovery strategies, and appropriate human intervention into the architecture.