• Own the Full Lifecycle: Build, scale, and maintain modern web applications where the heavy lifting sits in our Go backend, with the willingness to ship in React/TypeScript on the frontend whenever a feature calls for it. • Bridge the Gap: Design and implement clean APIs in Go while ensuring they are seamlessly integrated into a performant, accessible React frontend. • Architect for Scale: Maintain high standards for code quality and performance across the entire stack, from backend microservices to frontend component libraries. • Collaborate Broadly: Work closely with Product and Design to turn ambiguous requirements into polished features. • Agentic Engineering Mindset: You treat AI coding agents (Claude Code, Codex, and the like) as real collaborators, not autocomplete. You own every line that ships under your name, whether you typed it or an agent did. You're motivated to deep-dive into agent workflows and bring the judgment that turns agent output into production-grade code.

• Designing and building AI/LLM-assisted product features • Integrating LLM APIs into Ruby on Rails systems • Combining AI approaches with business logic, tests, fallbacks, and production safeguards • Owning features from technical design to production • Improving reliability, accuracy, consistency, latency, cost, security, and maintainability • Writing and maintaining automated tests, including unit, integration, and E2E tests • Debugging production issues and improving system behavior over time

• Own features from implementation to production within a well-defined product scope • Build and maintain robust Ruby on Rails systems used at scale • Work closely with product and other engineers to solve real user problems • Write and maintain automated tests (unit, integration, and E2E) • Improve performance, reliability, and maintainability of existing systems • Take responsibility for the quality and long-term health of what you build

• Owning features from technical design to production • Building and maintaining Ruby on Rails systems used at scale • Designing AI/LLM-assisted features and workflows where they improve product quality or user experience • Working with LLM APIs, prompts, retrieval/context strategies, and AI-assisted development tools • Making trade-offs around performance, reliability, cost, latency, security, and maintainability • Writing and maintaining automated tests, including unit, integration, and E2E tests • Debugging production issues and improving system reliability