The company builds AI voice agents that handle millions of live customer conversations for large brands, healthcare providers, and transportation companies. When the AI resolves a request such as a delivery status, a return, or a prescription refill, that is the work this team does.
The team is small and keeps a low profile. It focuses on hard problems and moves quickly. Outside the frontier AI labs, few groups run AI in production at this volume, and this team handles millions of live calls with an engineering group much smaller than you would expect.
The company holds engineers to a high standard. Decisions move fast, with no committee approval needed for work that clearly helps customers, so engineers ship directly to production.
Agentic development speeds up building, but production experience still matters. This role is for senior and staff engineers who can use faster tools with sound judgment.
The company cares more about how you build and whether you want to make product you are proud of than about specific stack experience or past employers.
The company is based in the US, the UK, and Canada.
The role reports to the CTO and is based in Marina del Rey, CA or Williamsburg, NY.
The work has three areas: vertical engineering on the agents and their customer integrations, platform engineering on the orchestration layer, and inference and DevOps, including the company's own model hosting, telephony, observability, and deployment.
The company also plans to extend its agents to chat. Work ranges from face-to-face customer engagement to deep backend systems, and your place on the team will be settled together as it grows.
The team uses Python, MongoDB, AWS, Twilio, Datadog, Snowflake, and Omni.
Responsibilities
Build agents that handle complex, multi-step customer workflows and integrate with contact center systems and industry systems such as orders, healthcare, and logistics.
Build and maintain the orchestration layer that agents run on, covering routing, state, and tool use, so vertical teams can ship without rebuilding it.
Help run low-latency model serving at production scale, along with telephony, observability, and deployment infrastructure for live calls.
Take on work close to customers or deep in backend systems, depending on where your strengths fit.
Own outcomes from start to finish, and ship working software instead of only proposing plans.
Requirements
Experience building and owning production systems where failures had real consequences. The team looks at what you have shipped and what you learned from it, not at years of work.
Sound judgment about what to ship, what to slow down on, and what should never ship, even when agentic tools make building fast.
A low-ego approach and a focus on delivering results.
A strong focus on the customer. You want to be close to the problem, sometimes in the room with customers, and measure success by what the customer receives.
Interest in either leading two or three engineers as the team grows or staying a hands-on individual contributor. Both paths are supported.
Conditions
Base pay ranges from $200,000 to $325,000 USD. Final pay depends on location, experience, and qualifications.
The role is in the office five days a week, with in-person collaboration.
Eligible for equity under company policy, subject to board approval.
The company is an equal opportunity employer and does not discriminate on protected characteristics.
Benefits
Comprehensive healthcare.
Unlimited vacation, with a mandatory half week off for everyone over July 4 and a full week off at the end of the year.
Where you’d work
From the office, 4 or more days a week in the office