AI Engineer

Ruby Labs is a leading tech company that creates and operates innovative consumer products across the health, education, and entertainment industries.

• Deep knowledge of Node.js & Next.js to build reliable services and handle complex LLM-generated data.
• Proven experience in building dynamic prompts dependent on input variables and context injection.
• Experience with OpenRouter APIs, managing rate limits, and selecting cost-effective models.
• Understanding of LLM observability principles, including tracing, test datasets, and scoring systems (Langfuse or similar).
• Experience with evaluation methodologies like RAGAS or custom “LLM-as-a-judge” systems.
• Analytical mindset to transform raw generation logs into actionable business metrics and technical insights.
• Iterative mindset focused on continuous product improvement through feedback loops.

Nice to have:

• Practical experience in fine-tuning models for specific domain tasks or JSON compliance.
• Understanding of Retrieval-Augmented Generation (RAG) architecture including indexing, retrieval, and re-ranking.
• Basic knowledge of Python for data science scripts or AI evaluation libraries.

• Advanced Prompt Engineering: Designing complex, dynamic prompt templates with conditional logic and efficiently reusing information and context within prompts to maximize generation quality and reasoning.
• Structured Outputs & Schemas: Implementing various response schemes (JSON mode, function calling, Zod/JSON schemas) to ensure AI outputs are predictable and ready for seamless integration into application logic.
• Prompt Engineering & Evaluations: Building robust evaluation pipelines and using Langfuse to collect feedback and score the quality of responses in real time.
• Tracing & Debugging: Performing deep debugging of complex LLM chains using Langfuse traces to identify bottlenecks and optimize for cost, latency, and context window usage.
• AI A/B Testing: Running systematic experiments across different models via OpenRouter and analyzing results based on quantitative metrics.
• Data-Driven Decisions: Making deployment decisions for new prompts or models strictly based on quantitative benchmarks and trace data.
• Output Scoring & Analysis: Developing scoring systems to analyze the “Problem → Solution” chain and identify root causes of hallucinations or logic errors using Langfuse analytics.
• Model Performance & Fine-Tuning: Regularly re-evaluating model performance as new architectures emerge and performing fine-tuning when necessary to meet specific domain requirements.

Applicants must be located within approximately ±4 hours of the Central European Time (CET) zone to ensure optimal collaboration and communication during working hours.