Loop / Harness Engineer. The role, the market signal, and how to build it in your org.
Builds the loops, tools and evaluation harnesses that agents run inside. Defines how an agent observes results, manages context, retries, stops and returns work for human review. Treat the title as a role grouping, not a forecast that it replaces prompt engineering.
In a workforce of people and AI agents, this role takes shape around the workflows it supports. Define its responsibilities and handoffs, then prepare people to perform that work.
Source snapshot 2026-07-17. Postings do not confirm that a vacancy is still open.
4 postings · 4 distinct titles · from 264,613 real job postings · see the source snapshot →
What the postings ask this role to do
38 tasks extracted from real Loop / Harness Engineer job descriptions, classified Automate / Augment / Human-only. In this source classification, 2.6% of task statements are automation candidates. The share does not measure working time or demonstrated agent performance.
- Follow defined scope, guidelines, and deadlines.
- 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.
- 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
From the market's version of this role to your version of it
Start with the work, not the org chart.
Define what this role will build, configure, decide and check. Connect that work to an enterprise-specific project and agreed assessment evidence.