AI Automation Engineer

• Run the scheduled measurement work and fix a run that fails, from the evidence of what failed.
• Keep a receipt for every observed answer, so each score can be traced.
• Keep answer scoring consistent across repeated runs of the same questions.
• Organize research and client evidence so the team can find any record it has published.
• Turn a task the team repeats by hand into one that runs the same way each time.
• Write down how each piece of repeatable work runs, so someone else can run it.

• Three or more years of engineering experience.
• Working depth in Python and JavaScript.
• Experience with workflow automation and with large language models in production.
• An example of a problem you diagnosed from logs or data rather than by guessing.
• Eligibility to work in the United States without visa sponsorship.

• Remote only, hiring in the United States. Relocation is allowed.
• The team works from Bloomington, Chicago, San Francisco and New York.
• The team sets its own hours across US time zones, and work is judged on output.

• Scheduled measurement runs complete, and every observed answer has its receipt.
• Repeated runs of the same question and engine score consistently under the published rules.

The method behind these measures is published on the methodology page.

$110k to $150k a year, full time, no equity. These are the bands as posted on Wellfound.

The role is also listed on Wellfound.

What you send is kept for twelve months and used only to assess your application. See the privacy notice.