AI Engineer - Ruby Labs

About Ruby Labs

Ruby Labs is a leading tech company that creates and operates innovative consumer products across the health, education, and entertainment industries. Our innovative teams drive the future of consumer-led products, delivering high-impact solutions globally.

About the Role

We are looking for an AI Engineer (Strong Middle / Senior level) to own and drive the quality, reliability, and evolution of our AI systems in production.

This is a high-ownership role. You will be responsible for end-to-end delivery of AI features, production stability of AI systems, and data-driven experimentation using tools like Langfuse and Cloudflare AI gateway for model routing. Increasingly, this includes agentic, tool-using AI systems: defining clean tool contracts (including MCP-based tools) and orchestrating how AI interacts with internal services, search, and background pipelines.

Tech Stack: TypeScript end to end (Node.js and Hono services on Cloudflare Workers with Durable Objects and Containers), PostgreSQL, OpenSearch, Langfuse, and multiple LLM provider integrations.

Key Responsibilities

AI Systems Ownership & Feature Delivery

• Take ownership of major AI features and LLM workflows, delivering them to production within agreed timelines.
• Own AI output quality, structure, and predictability across user-facing AI interactions, ensuring consistent structured output across different LLMs for the same request type.
• Integrate and orchestrate multiple LLM providers through an AI gateway, managing model selection, fallback strategies, and cost optimization.
• Design and orchestrate tool-using and agentic AI workflows, including clean tool contracts (MCP-based tools), function-calling interfaces, and reliable AI-to-system integrations.
• Build and maintain multi-step LLM workflows and RAG pipelines (indexing, embeddings, retrieval, re-ranking) for reasoning, context reuse, and search.

Prompt Engineering, Evaluation & Experimentation

• Design and manage production prompt systems with dynamic prompting, context injection, and conditional logic.
• Own prompt management, the release of LLM experiments, and Langfuse-based evaluation pipelines (test datasets, LLM-as-a-judge, output scoring).
• Run A/B tests across models and prompts, analyze the results, and present the data-driven impact of AI features and experiments.
• Deep-debug LLM chains using Langfuse traces: identify bottlenecks, optimize for cost, latency, and context-window usage, and root-cause hallucinations and logic errors.

Code Quality & Production Reliability

• Write clean, scalable, and maintainable TypeScript across the Node.js / Cloudflare Workers stack.
• Build reliable backend logic for AI systems: request and output validation, error handling, fallback flows for malformed or low-quality model responses, and reliable tool execution.
• Ensure high code quality through tests (including validation and fallback paths for AI output), code reviews, and clear engineering standards.
• Monitor AI system metrics, quality signals, latency, and release health, resolving production issues with documented root causes.
• Document prompt designs, model and routing choices, evaluation results, and architectural decisions.

Qualifications

• 4+ years of backend/fullstack software engineering experience with production-grade TypeScript/Node.js.
• 1+ year of AI/LLM systems in production with real users (beyond side projects or experiments).
• Daily experience with AI-centered development tools (Claude Code, Cursor, or similar).
• Deep hands-on experience with production LLM APIs (OpenAI, Anthropic, Google Gemini, etc.), including structured output, function calling, streaming, token management, and cost control.
• Experience with agentic AI, multi-step orchestration, tool-based workflows, or RAG pipelines.
• Experience with LLM observability and evaluation tools (Langfuse, LangSmith, or similar).
• Experience with AI gateways and model routing (OpenRouter, Cloudflare AI Gateway, or equivalent).
• Solid understanding of relational databases (PostgreSQL) and caching (Redis, KV, or similar).
• Exceptional ownership and personal responsibility for engineering quality and delivery.

Nice to Have

• Evaluation frameworks (LLM-as-a-judge, RAGAS) and building test datasets.
• MCP (Model Context Protocol): building MCP servers/clients or designing tool contracts for AI agents.
• Edge/serverless runtimes (Cloudflare Workers) and services (KV, Durable Objects, Queues, R2, Containers).
• Search engines and vector search (OpenSearch, Elasticsearch, pgvector) and embeddings.
• Background workflow engines (Hatchet, Temporal, Inngest) for high-volume LLM pipelines.
• Browser automation and browser agents (Playwright, CDP, browser-use).
• Practical fine-tuning for domain-specific tasks or strict JSON/schema compliance.
• Practical Python skills for data science, evaluation scripts, or AI tooling.

Location & Timezone

Ruby Labs operates within Central European Time (CET). Applicants from any country are welcome to apply, provided you are located within approximately ± 4 hours of CET for optimal team collaboration.

Benefits

• Remote Work: Freedom to work remotely from anywhere within timezone compatibility.
• Unlimited PTO: Take time off when you need it without counting days.
• Paid National Holidays: Paid time off to celebrate holidays.
• Equipment: Company-provided Apple MacBook.
• Contractor Agreement: Flexible Independent Contractor Agreement with autonomy and global flexibility.

Interview Process

1. Recruiter Screening (40 minutes)
2. Technical Interview (90 minutes)
3. Final Interview (60 minutes)