Summary
What you’ll impact
The Technical Writer - AI Evaluation creates clear, authoritative long‑form content that explains model performance, benchmark results, and emerging AI evaluation standards. The role leverages deep technical literacy in AI research, model evaluation frameworks, and industry benchmarks to translate complex papers and product capabilities into accessible narratives. Responsibilities include producing benchmark reports, product launch announcements, customer case studies, technical explainers, and occasional policy analyses. The writer collaborates closely with research, engineering, product, and customer teams, shaping content strategy and ghost‑writing for senior leaders.
Responsibilities
What you'll do
- Interview customers, researchers, engineers, and technical leaders and turn those conversations into strong long-form pieces.
- Help establish Vals Smith as the leading way for enterprises to evaluate models and agents on their own workflows through product launches, customer stories, technical case studies, and original analysis.
- Ghostwrite and edit for Vals leadership and technical team members when their perspective should be part of the conversation.
- Help decide what Vals should be writing about in the first place — not just execute against a content calendar.
- You’ll work closely with our research, engineering, product, and customer teams to turn technical work into sharp, accessible writing: benchmark reports, product launches, customer stories, model analyses, technical explainers, and occasional policy pieces.
- You’ll write across three parts of Vals: Vals Smith, our product for evaluating models and agents on the actual work companies do.; Our public benchmarks and research, where we independently measure frontier models across increasingly complex domains.; Emerging policy and standards conversation around AI evaluation, where rigorous measurement is becoming increasingly important to how labs, enterprises, and policymakers understand model capabilities.
Requirements
What you’ll bring
- A portfolio of long-form technical writing — published essays, research blog posts, lab posts, or industry reporting.
- Strong technical literacy. You don't need to be able to train a model, but you need to be able to read a paper, sit in on a research review, and come out with something accurate and sharp.
- An editorial point of view. You should have opinions about what's interesting, push back on weak takes, and not just transcribe what people say.
- Speed. We ship content the day a major model releases. You should be able to turn a publishable post in hours, not weeks.
- Ability to work in-person, in San Francisco. We will support your relocation as needed.
- Learning velocity: The role encompasses a wide variety of tasks. Rather than expecting you to be an expert on Day 1, we are looking for someone who can learn new skills and technologies quickly.
- Ownership: Working in a small, talent-dense team, we expect everyone to show initiative to build where it's needed, not where it's asked. We strive for autonomy over consensus.
- Intensity: The LLM landscape is constantly changing. Foundation model labs are continuously pushing the frontier. The unicorn companies that will emerge from this technology shift are being built now. Those that win will have an incredibly high speed of execution.
- Solution-oriented mindset: We're looking for people who see opportunities to craft solutions at each juncture, not those who pass hard problems to others or admit defeat.