[Remote] Software Engineer, Full-Stack (Agents)

Owner is building an AI-native platform that helps local business owners, starting with restaurants, succeed by replacing multiple tools. This full-stack engineer role focuses on building agent features that let restaurant owners manage their businesses through natural conversation, owning surfaces end-to-end from LLM integration to conversational UI. The position involves shaping agent architecture, backend orchestration, and evals to ensure fast and trustworthy production systems.

• Own one or more agent surfaces end-to-end, from LLM integration and tool design to backend orchestration, conversational UI, and evals
• Contribute to the shared agent platform: tool abstractions, chat persistence, eval frameworks, RAG, observability, permissioning
• Shape technical direction on agent architecture, framework choice, and model strategy
• Make thoughtful tradeoffs on latency, cost, and reliability so agents feel fast and trustworthy in production
• Raise the bar for agent quality through rigorous evals and patterns other engineers adopt

• 3+ years of software engineering experience with production LLM-powered or agentic features
• Fluency with tool calling, prompt engineering, and agent loops
• Experience with eval frameworks and observability for non-deterministic systems (Braintrust, LangSmith, or equivalent)
• Full-stack comfort across backend orchestration, tool design, and conversational UI