AI Engineer
Coval
Software Engineering, Data Science
San Francisco, CA, USA
Coval
Simulation & Evaluation that scales voice and chat AI agents
AI Engineer
About the role
THE ROLE
Coval is an expert in voice masquerading as an eval platform. We work with the companies at the frontier of voice AI, from Fortune 500s to the fastest-moving startups, and we see what's working and what's not across all of them. This role is about building the AI systems that make that expertise accessible.
This is an extremely high-agency role. You'll touch every part of our stack (simulations, UI, API, CLI) and decide where AI belongs and, just as importantly, where it doesn't. You're not building a simple chat agent or a help widget. You're building an AI system with full access to our platform that needs optimized tool calling, memory systems, and a data layer designed to provide immediate, concrete value.
Here's what that looks like in practice:
• Building the agentic form of Coval. What does our product look like when it's headless? What experiences belong in the UI versus a Claude-powered interface versus embedded in a code repo? You'll figure out where the puck is going and skate there.
• Developing AI systems that are genuinely useful. Optimize data retrieval, tool calling, and memory so our AI isn't just impressive in a demo. It helps customers get real answers about their voice agents, fast.
• Staying at the frontier of voice AI. We work with all the major labs and see the latest models before most people do. You'll help us understand what excellent voice architectures look like, which models to recommend for what, and how the space is shifting.
• Teaching the team. You're the kind of person others bring into a room to figure out how to use AI better. Not just in the product, but in internal workflows, tooling, and how the team operates.
Voice is becoming the primary way people interact with AI systems. The companies using our tools are the ones making that happen. You get to sit at that intersection and build the tooling they rely on.
WHAT WE'RE LOOKING FOR
• You're deeply immersed in AI. Not just using LLMs, but understanding how to build real systems on top of them: prompt engineering, evaluation, tool calling, memory, retrieval.
• You're creative and curious. You look at a product and see where AI should be and where it shouldn't. You have strong intuitions about what SaaS of the future looks like.
• You have high agency. You don't wait to be told what to build. You look at the company, the product, the customers, and you see what needs to happen.
• You've built AI-powered features in production, not just prototypes. You know the difference between a cool demo and something customers depend on.
• You're excited about voice AI specifically, or you're ready to go deep on it. We're consistently seen as experts in the space, and you'll help maintain that.
• You can move across the full stack when the problem demands it. This isn't a pure research role. You ship things.
WHAT YOU'LL WORK WITH
You'll work primarily in Python, building AI systems on top of LLM APIs with modern cloud infrastructure. When the problem takes you there, you'll also work across our TypeScript frontend. We invest in tooling that keeps iteration speed high.
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.