Staff AI Engineer

Staff AI Engineer We believe conversations will become the #1 way to shop. At Gorgias, we’re building the platform that makes this real: a unified AI agent that sells, supports, and re-engages customers across the entire journey. Conversational Commerce is the future of ecommerce, and we’re leading that shift. Our mission is to turn every interaction between a brand and its customers into a relationship: personal, seamless, and intelligent. By combining deep product expertise with the latest in AI, we’re making shopping feel more natural, human, and connected than ever before. To win, we focus relentlessly on: - Quality: conversations that feel authentic and on-brand. - Experience: effortless shopping from chat to checkout. - Re-engagement: personal, 1-1 dialogue instead of noisy marketing. The opportunity is massive. As AI reshapes how people buy, Gorgias is building the foundation for the next decade of ecommerce, where every brand has its own intelligent agent and every customer feels understood. Join us to make Conversational Commerce real. TEAM & CONTEXT Gorgias is an AI-first company building products powered by LLMs and agent-based systems. As we scale our AI capabilities, we need to improve how we evaluate, iterate, and operate these systems in production. Today, parts of this process remain manual or fragmented, especially around prompt iteration, validation, and evaluation workflows. This role will focus on building and scaling the systems that support AI evaluation and iteration, helping the team move faster and more reliably. ABOUT THE ROLE You’ll have a chance to: - 🤖 Work on production AI systems used by thousands of businesses - 🧠 Define how we evaluate and improve AI performance at scale - 🏗️ Build internal platforms and tooling used by AI and engineering teams - 📈 Reduce manual processes and improve iteration speed on AI features - 👥 Collaborate across AI, ML, and product teams - 🧑‍🏫 Raise the engineering bar and mentor others WHAT YOU’LL DO - Design and build systems for evaluating AI performance (offline and online) - Develop workflows and tooling for prompt iteration and validation - Improve the reliability, scalability, and observability of AI systems in production - Work closely with ML Engineers and AI Engineers to integrate evaluation into development workflows - Collaborate with product teams to ship AI-powered features - Take ownership of systems end-to-end, from design to production and monitoring - Contribute to improving engineering practices around AI development and evaluation - Mentor engineers and help structure how the team approaches AI engineering WHO YOU ARE - 8+ years of experience in software engineering - Strong backend engineering background - Experience building and scaling production systems - Experience working with AI systems (LLMs, agents, or similar) You likely come from one of the following backgrounds: - Staff or senior software engineer who has moved into AI systems - Engineer working on applied AI products in production - Experience building internal platforms or developer tooling WHAT YOU’LL DO 1. Architect the Evaluation "Factory" - End-to-End Platform Ownership: Architect and lead the development of our internal evaluation platform, moving the needle from manual testing to a fully automated lifecycle (from LLM-as-a-judge creation to production monitoring). - Accelerate Time-to-Market: Directly impact our primary KPI by designing tools and workflows that drastically reduce the time it takes to deliver a calibrated, production-ready agent. - Infrastructure Collaboration: Partner with the Orchestration team to build the robust, scalable infrastructure required to run complex evals and agentic simulations at scale. 2. Scaling AI Expertise - Squad Empowerment: Serve as the "AI Technical Lead" for product squads, guiding them through the complexities of agent design, failure analysis, and prompting best practices. - Decentrali ... (truncated, view full listing at source)