About the role
Ruby Labs is hiring an AI Engineer to own production AI features and LLM workflows across its consumer products. The role covers the full path from implementation to production reliability, including consistent structured outputs, model routing, fallback strategies, and cost and latency optimization. The stack includes TypeScript, Node.js, Cloudflare Workers, PostgreSQL, OpenSearch, and multiple model providers.
You will build agentic workflows, tool integrations, and RAG pipelines, then evaluate their quality through Langfuse traces, test datasets, LLM-as-a-judge, and A/B experiments. The role also includes monitoring production metrics, resolving incidents, documenting architecture, and maintaining code quality. Applicants need 4+ years of backend or full-stack engineering experience and at least 1 year working with production AI/LLM systems. The position is remote for applicants within approximately four hours of Central European Time.
Highlights
- Own delivery and reliability of production LLM features.
- Build agentic workflows, MCP tool contracts, and RAG pipelines.
- Run prompt and model evaluations, experiments, and A/B tests.
- Remote work, unlimited PTO, and a company-provided MacBook.
This recap is dataskew's editorial summary, not the company's copy.