Lead Engineer - AI Studio

We're looking for a Lead Software Engineer to join our AI Studio Team, the group responsible for building AI Studio an AI-based React application builder that generates production-ready websites and other React applications from natural language, which users can then connect to custom domains and publish live to the internet from prompt-driven app generation, component and layout creation, automated copy/design generation, real-time preview and editing, to one-click deployment across our product ecosystem.

This team owns the intelligence layer that helps millions of SMBs build production-ready websites and React applications without technical expertise. The AI Studio platform orchestrates complex workflows across data processing, LLM-powered reasoning, code and component generation, design generation, and live deployment to custom domains. With millions of applications and billions of visitor interactions flowing through our systems, reliability, correctness, and performance are mission-critical.

As a Lead Engineer, you will drive the technical direction for our AI-driven application-builder architecture, lead complex system design decisions, and serve as a hands‑on technical leader and mentor for the engineers building AI Studio's app generation engine, React website/app builder, design and component systems, domain publishing pipeline, and AI Agents. This is a hands‑on individual contributor role you'll spend the majority of your time designing systems and writing production code while partnering closely with product, infra, and design to shape the roadmap, raise engineering standards, and deliver intuitive, generative, high-performance user experiences at scale.

The candidate will have responsibilities across the following functions:

• Own architecture and scaling decisions for core AI Studio platform components (e. g., App Generation Engine, React Build & Render Pipeline, Domain & Publishing Pipeline, AI Content Systems).
• Lead design and implementation of cross‑cutting initiatives to improve system responsiveness, generation accuracy, and platform robustness.
• Build scalable, fault‑tolerant LLM pipelines for content generation, layout creation, experimentation, and AI‑driven user guidance.

• Work hands‑on with technologies like Go, NestJS, Node, PostgreSQL, Firestore, Vector Databases, Cloudflare Workers, Cloudflare KV, and microservices.
• Design distributed systems that handle high‑throughput generative and analytical workloads while ensuring correctness and low latency.
• Build and optimise embeddings pipelines, retrieval‑augmented generation (RAG), and multi‑agent orchestration frameworks.

• Drive improvements in observability using Prometheus/Grafana, Open Telemetry, and structured logging.
• Establish and maintain SLOs for generation latency, correctness, model safety, and system uptime.
• Strengthen resiliency and failover strategies to ensure seamless user experiences during traffic spikes and model load variations.

• Implement hallucination mitigation strategies (code constraints, structured outputs, model verification layers, retrieval guards, test scaffolding).
• Collaborate with infra and security to enforce data governance, access control, privacy boundaries, and compliance around user‑generated data.
• Leverage LLMs and AI tools to write, test, and debug code while driving standards that ensure reliability and consistency across engineering teams.

• Mentor engineers through code reviews, design discussions, and pairing, leading by influence to promote technical excellence, code quality, and a high‑ownership culture (this is an individual contributor role with no direct reports).
• Partner with PMs, designers, and other engineering leaders to define long‑term roadmap and deliver high‑performing AI‑powered application‑building features.
• Participate in reviews, deep dives, and on‑call rotations to maintain a culture of accountability and operational excellence.

• 6+ years of backend engineering experience, including…