🛠 Tech Stack

💼 About This Role

You'll shape AI infrastructure and drive production-ready LLM experiences at Ruby Labs. You'll own advanced prompt systems and complex LLM workflows, making data-driven decisions around model performance and cost. This role offers end-to-end ownership from experimentation to live production.

🎯 What You'll Do

• Design complex dynamic prompt templates with conditional logic
• Implement structured output schemas like JSON mode and function calling
• Build evaluation pipelines and use Langfuse for real-time scoring
• Run A/B tests across different models via OpenRouter

📋 Requirements

• Node.js & Next.js expertise
• Dynamic prompting skills for context-dependent content
• OpenRouter experience with unified APIs and rate limits
• Langfuse (or similar) for LLM observability and tracing

✨ Nice to Have

• Fine-tuning models for domain-specific tasks
• RAG architecture knowledge including indexing and retrieval
• Python for data science scripts or evaluation libraries

🎁 Benefits & Perks

• 🏖️ Unlimited PTO
• 💻 Company-provided MacBook
• 🌍 Remote work environment
• 🎉 Paid national holidays
• 📄 Flexible Independent Contractor Agreement

📨 Hiring Process

Estimated timeline: 2-3 weeks

1. 1Recruiter Screening· 40 min
2. 2Technical Interview· 60 min
3. 3Final Interview· 30 min