Number of Applicants
:000+
Let AI Supercharge Your Job Hunt!
JobCopilot scans 500,000+ company career sites daily to find jobs for you
Location: San Francisco (in-person, in-office, full-time ONLY)
Compensation: $130k-$200k base + $25K-$50K cash bonus
Virio is building the content engine for AI-native executives, and the hardest part of that problem is making AI output you can actually trust.
Great content can't be a lucky generation. It has to be reliable, repeatable, and right every time. That means the harness around the models matters as much as the models themselves: the orchestration, evals, guardrails, and agentic scaffolding that turn raw generation into content executives will put their name on.
We're backed by operators from LinkedIn, YouTube, HubSpot, Rippling, and Google. We've added $1M ARR in 30 days. And the way we think about content generation, agentic systems, and human-in-the-loop workflows doesn't have an established playbook.
We're looking for a Harness Engineer to own that layer end to end: building the systems that measure, constrain, and improve what our models produce, so quality scales with us instead of breaking as we grow.
As a Harness Engineer, you'll own the intelligence layer that sits between our AI models and product—the system prompts, tool definitions, context management, and evaluation framework that makes agents actually work in production.
Specifically:
Build and refine the system prompts, tool integrations, and context windows that shape how our models behave across our platform—you'll see how small prompt tweaks cascade into measurable product impact. (Nice to have: background in English, literature, creative writing, or humanities)
Design the evaluation framework (LLM-as-judge evals, deterministic tests, production monitoring) that lets us ship with confidence. You'll define what success looks like and build the metrics to measure it.
Architect the abstraction layer between our product (file systems, artifacts, skills) and the model's capabilities—making complex multi-step workflows feel natural to the model and reliable to users.
Own prompt versioning, experimentation, and iteration. You'll A/B test prompt variations, measure their impact on agent quality, and ship improvements across our production system.
Collaborate with product and engineering to identify signal—where our agents are failing, where users are stuck—and translate that into prompt and architecture improvements.
After 30 days: You understand our agent stack—the system prompts, available tools, context window strategy, and current failure modes. You've shipped your first prompt improvement and measured its impact.
After 90 days: You've designed and implemented our core evaluation framework. Our team uses it as the source of truth for agent quality. You've shipped 2-3 meaningful prompt iterations that improved measurable outputs, and you're comfortable making architecture trade-offs.
After 6 months: You own the harness layer end-to-end. You've architected improvements that reduced hallucination, improved context retention, or increased model reliability. You're driving architectural decisions about how we expose capabilities to the product team. You're writing technical content about how we've solved these problems—attracting the next generation of harness engineers to the company.
High agency & self-direction – Acts without waiting for requirements or detailed instructions
Small-team intensity comfort – Comfortable working intensely and closely with a small, high-output team
Unorthodox problem solving – Sees non-obvious paths forward and challenges conventional approaches
Quality-driven execution – Detail-oriented with high standards for correctness and quality
Low ego & accountability – Takes full ownership and accountability for outcomes
Work directly with the founders
Competitive total compensation aligned to impact and ownership
Meaningful equity upside as part of the founding team
Medical, dental, and vision insurance
401(k) plan
All working meals covered
Relocation support for San Francisco
Company-wide annual off-site
High ownership, high trust, and fast career progression alongside world-class client partners
In-person culture with deep commitment to excellence
This is a full-time, on-site role based in San Francisco. We do not offer hybrid or remote positions.
Auto-Apply to Harness Engineer Jobs with your AI JobCopilot
Copyright © 2026 Grabjobs Pte.Ltd. All Rights Reserved.