New Roles · Engineering AI Builders

Loop / Harness Engineer. The role, the market signal, and how to build it in your org.

The 2026 successor to the Prompt Engineer. Instead of prompting an agent step by step, designs the loop and harness the agent runs inside: the scaffolding of tools, memory, verification, and the act-observe-decide-repeat cycle that keeps an agent productive, on-goal, and verified while it runs unattended for hours. When a single agent run touches dozens of files, the leverage moves from writing a sharper prompt to designing a better loop. A skill in formation, named by practitioners at Anthropic, Google, and the frontier labs ("beyond prompt engineering", "thin harness, fat skills"), not yet a job-board title. The signal lives in commentary and practitioner writing, not postings.

4 postings · 4 distinct titles · from 264,613 real job postings · see the live data →

What the market calls it
Loop EngineerHarness EngineerAgent Loop EngineerAgent Harness Engineer
Hiring this role in our corpus right now
Aptiv 1Cohere 1Cursor 1Openai 1

What the postings ask this role to do

38 tasks extracted from real Loop / Harness Engineer job descriptions, classified Automate / Augment / Human-only. Only 2.6% can be fully automated: companies are hiring this role for the judgment, not the keystrokes.

Automate
  • Follow defined scope, guidelines, and deadlines.
Augment
  • Design agent orchestration.
  • Develop tools for agent interactions.
  • Launch new models on cursor end-to-end.
  • Tune model behavior for agent performance.
  • Perform tests and issue root cause analysis.
Human-only
  • Mentor other team members.
  • Shape the default cursor agent's personality.
  • Ensure evals are the shared bridge between both teams
  • Ensure that as the harness evolves the model evolves with it
  • Own the feedback loop between north's harness and the modeling team
How we build it in your org

From the market's version of this role to your version of it

1. Audit the work
Start Your Transition maps the tasks this role would own in your operation and classifies each one: what AI runs, what your people run with AI, what stays human.
2. Define your version
Your team composes the job description for your org's variant of the role, grounded in the audited tasks rather than a copied template.
3. Make people ready
A readiness plan built from that job description, delivered in GenAI Sandboxes with Simulations and Competency Assessments. Readiness is demonstrated, not assumed.
Build your own

Compose your org's Loop / Harness Engineer job description

Start from the tasks real postings ask for, keep the ones that match your operation, add what is specific to you. The tasks carry their AI classification, so the JD you take away already says what AI runs and what stays with people.

Start with the work, not the org chart.

Run the audit on one operation and see what this role would own first.