Job description
Skills We're Looking For Strong Python skills with FastAPI and Pydantic. TypeScript is a plus.Experience with LLM APIs and Agentic frameworks. You've built applications using frontier models and understand prompt engineering, function calling, and structured outputs.Voice AI experience. You've worked with STT/TTS services like Deepgram or ElevenLabs and voice agent frameworks like LiveKit, Pipecat, or Vapi. You understand real-time audio pipelines, turn-taking, and latency optimization.Familiarity with agent interoperability protocols such as A2A and MCP, and an understanding of how agents connect to tools, data sources, and each other.Problem-solving mindset where you break down complex problems and find practical solutions—knowing when a simple prompt chain is enough versus when a full agent architecture is warranted.Clear communication so you can explain technical concepts to anyone, gather requirements effectively, and document system behavior for teammates.Production experience deploying and maintaining real cloud-native applications with proper observability and reliability practices.RequirementsWhat You'll Do Build AI-powered applications that automate workflows, assist teams, and enhance customer experiences across our restaurant technology platformDesign and develop voice AI solutions including conversational agents, phone-based ordering, and real-time customer supportArchitect Agentic systems—single-agent and multi-agent—that can reason, plan, and execute complex tasks with appropriate human oversightConnect AI systems to company data and services so they can answer questions and take actions based on real informationTranslate business needs into technical solutions, working closely with non-technical stakeholders to understand problems before jumping to codeMonitor and improve deployed AI systems by tracking performance, evaluating outputs, and optimizing for reliability, latency, and costBonus Experience deploying voice or conversational AI agents in productionBroader voice stack knowledge spanning VAD, speech recognition, synthesis, orchestration, and telephony integration via Twilio, Telnyx, or similarExperience building multi-agent systems or production MCP serversHands-on work with agent SDKs such as OpenAI Agents SDK, Google ADK, LangGraph, or similarFamiliarity with vector databases like pgvector, Pinecone, or Weaviate and RAG patternsBackground in model evaluation or building quality pipelines for AI outputsExperience with real-time communication infrastructure such as WebRTCContributions to open-source AI tooling or published technical writing