The Mission:We are building AI agents that work for restaurants. Our agents answer calls, take orders, book reservations, and handle cateringall through a natural, human-like voice. We meet restaurants where they are, building automated systems that understand the chaos of a real kitchen.
What We Do
As an AI Engineer here, you'll turn cutting-edge research into production-ready voice, text, and video-based agents that serve real customers every day. You'll collaborate with a tight-knit product and research team, rapidly deploying models that directly impact how businesses run.
We move fast, trust deeply, and iterate constantly. This role is remote, but you will be fully integrated into a team that operates with a high-density, in-person energy.
What You'll Do
- Real-World Optimization:Fine-tune ASR (Speech-to-Text), LLM, and TTS (Text-to-Speech) models for busy, noisy, and high-stakes restaurant environments.
- Agent Architecture:Build and scale Retrieval-Augmented Generation (RAG) systems, Reinforcement Learning (RL) loops, and sophisticated prompt engineering for context-aware conversations.
- 0 1 Prototyping:Rapidly build new agent capabilities from scratch, then lead the transition from1 Nfor mass deployment.
- End-to-End Integration:Connect AI components into seamless agents that handle complex logic like takeout flows, catering, and dynamic scheduling.
- Quality Loops:Create human-in-the-loop and automated feedback systems to monitor performance and drive continuous improvement based on real customer data.
Basic Qualifications
- 57+ Years Experience:A proven track record of building production-ready AI systems (Voice, NLP, or Agent-based). We value battle scars over years on a resume.
- Latency Obsession:Experience building systems optimized for low-latency and resource efficiency (essential for natural voice conversation).
- Mindset:A strong analytical, data-driven approach and a passion for creating frustration-free AI experiences.
- Academic/Hands-on Mix:BS, MS, or PhD in CS/AI/Math, or equivalent high-level hands-on expertise in the field.
Preferred Qualifications
- GCP Expertise:While we use multiple clouds, deep experience withGoogle Cloud Platform(Vertex AI, BigQuery, etc.) is a huge plus.
- WebRTC Mastery:Experience with stacks likeLiveKitfor real-time audio/video streaming.
- Tooling:Experience building robust REST APIs for LLM tool-calling and orchestration.
How We Work
- Leverage:We invest in great internal tools, fast CI/CD, and scalable code so you can focus on the AI.
- Ownership:Engineers here talk to users, design features, and ship fast. There is no hand-off culture.
- Clarity:We value building over process. Fewer meetings, more code.
