Harness Engineer
About The Position
Virio is solving an unsolved problem: how do you write perfect content? The best human strategist researches the space, finds the angle, and knows your goals and constraints — but they're capped by the hours in a day and one human career's worth of expertise. An agent isn't. Crafting "perfect" content has three components: 1. Research: to identify and collect the best inputs 2. Synthesis: to devise the strategy and execute on it 3. Verification: RL verification of content quality and efficacy We're backed by operators from LinkedIn, YouTube, HubSpot, Rippling, and Google. The team is almost 100% ex-founders and VCs from Yale, UC Berkeley, Stripe, and more. And we've consecutively added $1M ARR/mo because everyone and their co-founder wants what we're selling. This problem doesn't have a playbook. We're looking for a Harness Engineer to obsess over AI-for-writing and own that layer end to end: the data feedback loop, evals, and harness design that turn a subjective judgment into something we can measure and improve — so day by day, we can get ever closer to solving content.
Requirements
- 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
Nice To Haves
- background in English, literature, creative writing, or humanities
Responsibilities
- 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.
- 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.
Benefits
- 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
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Entry Level
Education Level
No Education Listed
