ai engineer

Ruby Labs is a technology company that develops and operates consumer products across the health, education, and entertainment industries.

• Deliver major AI engineering features within agreed timelines;
• Own AI output quality, structure, and predictability across user-facing interactions;
• Design, implement, and maintain output-type-based AI systems, including segmentation, routing, and enforcement;
• Ensure consistent output structure and formatting across different LLMs;
• Integrate and orchestrate multiple LLM providers via OpenRouter, managing model selection, fallback strategies, and cost optimizations;
• Design and orchestrate tool-using and agentic AI workflows, defining tool contracts and function-calling interfaces;
• Build and maintain complex, multi-step LLM workflows using orchestration frameworks for advanced reasoning, context reuse, and retrieval;
• Design and manage production prompt systems with dynamic prompting, context injection, and conditional logic;
• Own the deployment and release of LLM experiments, prompt management, and evaluation pipelines;
• Run A/B tests across models, analyze results, and present data-driven impact assessments;
• Monitor AI system metrics, quality signals, latency, and release health;
• Debug complex LLM chains, identify bottlenecks, and optimize for cost, latency, and context-window usage;
• Write clean, scalable, and maintainable TypeScript code;
• Build reliable backend logic for AI systems with error handling, request validation, and fallback flows;
• Ensure high code quality through testing, code reviews, and engineering standards;
• Monitor, troubleshoot, and improve production performance and system health;
• Drive maintainability and technical quality through architecture, refactoring, and release practices.

• 6+ Years of backend/full-stack software engineering experience, including production-grade TypeScript/Node.js;
• 2+ Years of experience building AI/LLM systems in production;
• Deep hands-on experience working with LLM APIs in production environments;
• Experience with Agentic AI, multi-agent orchestration, tool-based workflows, and RAG pipelines;
• Experience with LLM observability tools such as Langfuse or LangSmith;
• Experience with AI gateways and model routing solutions;
• Solid understanding of Redis and PostgreSQL;
• Exceptional ownership mindset and personal responsibility for engineering quality;
• Nice to have: Experience with AI-centered development tools (Cursor, Claude Code, Windsurf), familiarity with evaluation frameworks (LLM-as-a-judge, RAGAS), experience in high-pressure startup environments, experience with MCP, experience with edge and serverless runtimes (Cloudflare Workers), experience with payments/billing flows, practical experience fine-tuning models, working proficiency in Python.

• Unlimited PTO;
• Paid national holidays;
• Company-provided MacBook;
• Flexible independent contractor agreement.