AI Engineer, Evals & Agent Quality
At a glance
Mid-level AI Engineering role at Town.com, Inc. San Francisco · full-time · $250,000–$300,000 base.
aimlroles summary, based on the employer's posting.
What you'll do
- Build quality tests that assess the assistant across its different product surfaces and the full sequence of actions it takes
- Create reference datasets and a labeling process that stays current and catches quality gains or regressions
- Develop model selection and live evaluation tools to guide which models handle different tasks
- Make prompt and system updates measurable, then work with product engineers to turn quality signals into fixes
What you bring
- You have built or owned LLM evaluation systems, or measured model quality offline and online at scale
- You bring a rigorous approach to deciding what counts as better, regardless of your exact training path
- You have practical familiarity with evaluation frameworks and can reason through model-routing tradeoffs
Who this fits
This suits a senior or staff-level engineer who is comfortable building a new system from the ground up and implementing fixes, not only tracking metrics. You’ll work in person five days a week at the Financial District office in San Francisco.
From the employer
About Town
Town is building the AI coworker for every team. Everyone gets their own Townie, an AI assistant that learns how you work (your voice, judgment, relationships, and priorities) and does real work on your behalf across email, calendar, docs, Slack, and CRM. Townies don't wait to be prompted. They observe, learn, and act. And because every teammate has one, Townies can ask each other questions and hand off work, so the whole team moves faster together.
Four months after our public launch, we became a $1B company. We recently raised a $108M Series B, co-led by Forerunner Ventures and Menlo Ventures, with continued support from Andreessen Horowitz, First Round Capital and angels such as Zach Perret, Soleio Cuervo, Scott Belsky, and more. Our founders, Jean-Denis and Tony, previously led EPD at Plaid and applied AI product at Google.
About the role
Town is building the most personalized, most capable AI assistant for everyone — one that knows you deeply, works across every tool you use, and gets sharper over time. Building the best assistant means proving it's the best: every model, prompt, and system change has to be measurably better, on every surface it touches.
That's what you'll own. You'll build the evals and quality systems that turn assistant performance into numbers the whole team can trust, measuring and improving the full multi-step trajectory the assistant takes to do real work. You'll build the model routing that puts the right model in the right place balancing cost, quality, and speed.
This is a foundational, 0→1 build with ownership to match: the eval framework, the golden datasets and labeling loop, model routing, and online measurement, and you set the bar for what "best" means at Town.
What you'll do
Build a generalized eval system that measures assistant quality across every surface it touches — and, crucially, across multi-step agent trajectories.
Stand up golden datasets and the labeling loop that keeps them up to date and constantly checking to validate improvements and avoid regressions.
Build model routing and online evaluation tooling to help us learn and route to the best models.
Make every prompt and system change measurable, so the team can move fast without breaking what works.
Partner with engineers across the product to instrument quality and close the loop from signal to fix.
You might thrive here if you...
Have built or owned LLM eval systems, or offline/online quality measurement at scale.
Think rigorously about measurement. Maybe that came from an MLE or applied-ML background, maybe not, the instinct for how to measure "better" matters more than the exact pedigree.
Know the eval landscape hands-on, off-the-shelf tooling and eval frameworks, and have opinions on what to reach for when.
Are comfortable reasoning about model routing and the tradeoffs between models.
Ship the fixes, not just the dashboards and metrics.
Are a senior or staff engineer comfortable in greenfield, where the system doesn't exist yet.
Location
San Francisco, CA. Five days a week in person at our Financial District office.