Remote
- Discuss this with your agent
- Open in Claude
- Open in ChatGPT
Prepare application
- Draft this with your agent
- Open in Claude
- Open in ChatGPT
Role details
Tech stack
Job description
Own the architecture and technical direction of conversational AI and voice-ordering systems. Design reliable, low-latency backend services for live drive-thru traffic, lead cross-system integrations with POS and hardware, improve AI evaluation and observability, mentor engineers, and resolve complex production issues involving real-time audio, distributed services, and third-party integrations. The summary above was generated by AI, 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. Done well, this means more revenue, faster lines, and fewer mistakes for the operators we serve. As a Staff Software Engineer, you’ll take ownership of the hardest technical problems across our stack including backend and AI systems: designing for reliability, speed and accuracy under live drive-thru traffic. This is a high-leverage, high-autonomy role for someone who wants to shape the technical direction of a fast-moving product, not just execute tickets. What You’ll Do
- Design and evolve the core architecture of our conversational AI and voice-ordering systems, balancing latency, reliability, and correctness in a live, in-lane drive-thru environment
- Lead complex, cross-cutting technical initiatives - from POS and hardware integrations to evaluation and observability of AI agent behavior - that span multiple systems and teams
- Set technical direction and standards for the backend, and mentor and onboard new hires.
- Partner closely with product and operations to translate the real-world, on-the-ground needs of local business operators into robust technical solutions
- Improve how we test, evaluate, and monitor AI agent quality, given the unique challenges of validating non-deterministic, conversational systems
- Debug and resolve the gnarliest production issues, especially ones spanning real-time audio, third-party integrations, and distributed services
Requirements
- 8+ years of professional software engineering experience, with a track record of owning significant systems end-to-end
- Deep experience with backend systems in Python (or similarly strong general backend fundamentals with a willingness to go deep in Python)
- Experience designing for reliability and correctness in real-time or latency-sensitive systems
- Comfort operating with ambiguity - you can take a loosely defined problem and drive it to a well-architected solution
- Strong judgment about when to build for scale vs. when to move fast - and the communication skills to bring others along with your reasoning
- Bonus: experience with conversational AI/LLM-based systems, real-time audio/telephony platforms, or integrating with third-party/legacy POS or specialized hardware
About the company
You’ll have significant influence over both the product and the 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.
Apply for this position
This job is hosted externally. Click below to view the full posting and apply.
Prepare application
- Draft this with your agent
- Open in Claude
- Open in ChatGPT
Good distractions
Talks and stories from around this role — technically off-topic, practically not.
Moments
Explore playlistsVideos
See allRelated articles
See all
Dev Digest 137 - AI'm not sure about this
Never delegate the understanding
How We Built a Worry-Free System That Runs for 10+ Years – And What We’d Do Again
Dev Digest 121 - AI goes offline