About the Role
At
Arc
, we are on a mission to amplify employees at local businesses using AI. With years of experience building and scaling commerce tools for businesses—from farmers markets and neighborhood coffee shops to global retailers, restaurant chains, and major sports venues—we know how to deliver mission-critical technology that integrates easily, delights customers, and works every time.
Voice drive-thru is our first product on that journey: an AI voice agent that takes real orders at the drive-thru speaker, in real time, integrating directly with a business's existing POS and hardware. Every order is a live conversation with a real customer — no undo button, no retry. Getting it right means building agents that are accurate under noisy audio, fast enough to feel natural, and tuned to actually grow revenue for the operators we serve, across brands with very different menus and POS systems.
As a Senior Applied AI Engineer, you'll own the end to end AI engine that powers our agents today. We have a pretty sophisticated AI stack that you'll be owning and continuously making improvements to it including researching and experimenting with new AI techniques, and rolling it out so that our agent is backed by the latest and greatest AI. This is a high-leverage, high-autonomy role for someone who wants to make a non-deterministic system demonstrably better every week, not just ship a prompt and hope.
What You'll Do
Design and iterate on our conversational and order taking agent logic across multiple restaurant brands
Own difficult problems like turn taking, background noise removal, side conversations, etc.
Build and extend our evaluation infrastructure
Work closely with POS and menu data to make sure agent behavior — recommendations, substitutions, pricing — stays correct as brands, menus, and integrations evolve in realtime
What We're Looking For
5+ years of professional software engineering experience, with significant hands-on experience training ML models from scratch and productionizing them at scale
Strong Python skills and comfort working in a real backend codebase, not just notebooks
Experience designing evaluation systems for non-deterministic outputs
A track record of turning ambiguous quality problems into measurable metrics and concrete fixes
Strong judgment about when to generalize agent behavior vs. specialize per brand/customer, and the communication skills to bring others along with your reasoning
Bonus: experience with real-time/voice conversational agents, revenue or recommendation systems, or multi-tenant prompt/config management
Why Join Us
You'll have significant influence over both the product and the AI engineering culture at an early-stage company solving a genuinely hard, high-stakes problem: real-time AI that talks to real customers, in service of a mission to help local businesses run better. Voice drive-thru is just the beginning — your decisions will help shape what comes next.