> Markdown version of [/jobs/ext/4114518-senior-ai-engineer](https://www.wearedevelopers.com/jobs/ext/4114518-senior-ai-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Senior AI Engineer - **Company:** Ruby Labs - **Location:** France (Remote available) - **Experience:** Expert - **Contract:** Permanent contract - **Skills:** Artificial Intelligence, Business Logic, JSON, PostgreSQL, Node.Js, Ruby, Next.js, Software Engineering, TypeScript, Large Language Models, Llamaindex, Langfuse — LLM Observability and Analytics Platform, Playwright, RAGAS (Retrieval Augmented Generation Assessment), Cloudflare, Invoking Functions, Prompt Templates, Serverless Computing - **Published:** October 22, 2026 - **Apply:** https://www.indeed.com/viewjob?jk=91862ba66d7e2ac0 ## About the Role * (5+) years of software engineering with Node.js, TypeScript, Next.js, and Postgres, including edge or serverless runtimes such as Cloudflare Workers * Production browser automation with Playwright (Browserbase or similar): resilient selectors, retries, failure handling at scale * Production experience with dynamic prompting - content that depends on input variables and injected context * Structured outputs in production: JSON mode, function calling, Zod/JSON schemas * Experience with unified LLM APIs or AI gateways (OpenRouter, Cloudflare AI Gateway): rate limits, fallbacks, cost-effective model selection * LLM observability with Langfuse or similar: tracing, test datasets, scoring integration * Evaluation methodology: RAGAS or custom LLM-as-a-judge systems ## Description We are looking for a Senior AI Engineer to own and scale the AI layer of one of our core D2C subscription products. You will be fully responsible for production LLM features and the browser automation built around them end to end - prompt systems, structured outputs, evaluation, observability, and model selection - from first experiment to live release, with quality, reliability, and cost as your accountability. This is a high-impact role suited for someone who decides with data, not intuition. Unmeasured prompt changes, untraced failures, and model swaps without benchmarks are not acceptable. You work in a modern TypeScript stack - Next.js, Cloudflare Workers and Containers with Hono, Hatchet task queues, Drizzle on Supabase Postgres, Vercel Blob. Browser automation on Browserbase and Playwright is roughly half of the job., * Build evaluation pipelines - test datasets, LLM-as-a-judge, RAGAS-style metrics - and score responses and screen classifications in Langfuse * Trace complex LLM chains to find bottlenecks in cost, latency, and context-window usage * Run A/B experiments across models and prompts through an AI gateway (OpenRouter, Cloudflare AI Gateway); release only on quantitative benchmarks * Re-evaluate models as new architectures emerge; fine-tune when domain requirements demand it, * Take AI features from experiment to live production on Cloudflare Workers and Containers, and stay accountable after release * Manage rate limits, fallbacks, and model cost so features stay reliable at scale * Resolve production incidents in owned AI and automation systems with documented root-cause analysis, * Analytical - converts generation logs into metrics a business can act on * Iterative - builds feedback loops and improves continuously * Owns the outcome from experiment to production, and after * Verifies before trusting - treats LLM output as unproven until validated