Senior Platform Engineer

About the role

The role

Own the systems behind Coval’s evaluations. Coval is the evaluation platform for conversational AI: we help enterprise teams simulate before launch, observe in production and review with humans. This role owns the machinery that makes all of it run.

That means the distributed pipelines, queues and orchestration that score tens of thousands of conversations a day, plus the data layer and cost controls underneath them. You’ll own the systems enterprises run their voice agents through, and you’ll get in while they’re still being built.

What you’ll do

• Build out our distributed execution engine: the workers, queues and orchestration that fan out tens of thousands of simulated conversations a day and bring back scores
• Own the data side, from the databases holding conversations, audio and judge results to the pipelines that move them between stages
• Make real cost trade-offs. Every model call and storage byte has a price, and you keep unit economics sane as volume climbs
• Stand up and maintain the environments where our LoRA training jobs run, as a key part of the plumbing for our ML work

What we’re looking for

• 4+ years building real systems, with Python and AWS as home turf
• Experience with managed services and Terraform, which we use heavily, and the judgment to know when a managed service stops being the right answer
• You’ve operated something under load and know what it feels like when a queue backs up at 2am
• You can look at a half-built system and decide what to finish, what to fix, what to start next and what to buy time on
• High agency: on a small Series A team, nobody writes your tickets. You figure out what matters next and take it there
• Ambitious and kind. As a founding member of the engineering team, you’ll shape the architecture and the standards everyone else builds against

About Coval

What Coval Does

Coval is the simulation and evaluation platform for voice AI. We help companies answer the question most can't: do their voice agents actually work? Not in a demo. At scale, in production, with real users.

Most teams building voice agents are flying blind. They ship a demo that works, deploy it, and discover weeks later that 40% of conversations are failing. No evaluation infrastructure. No way to catch regressions before users do.

We built Coval because we've seen this movie before. Brooke led evaluation infrastructure at Waymo, where it takes millions of simulated miles before a vehicle touches a public road. Voice agents need the same rigor. Right now, almost nobody has it.

Nine people, backed by YC, closing six-figure enterprise deals with Fortune 500 companies, growing revenue 10x year over year. The space is moving fast. We're at the center of it.

What It's Like Here

We work in-person in SoMa, San Francisco. The office is shoes-off, full of plants, and dog-friendly. We bike, hike, skate, and run half-marathons together.

The team comes from Waymo, Zoox, Apple, and Google. We're hard on our work but never hard on each other. We ship on Sundays because we want to, not because someone told us to. We move at AI speed: what used to take weeks happens in hours.

Our operating principle is "wholesome and unhinged." We are relentless about making things happen, but we don't take ourselves too seriously. If you thrive in ambiguity, move fast, and want to be one of the first people building the sales foundations at a company that's already closing Fortune 500 deals, this is it.

Voice AI is where the market is going. We're already there. This is the best time to join.