🛠 Tech Stack

💼 About This Role

You'll shape AI infrastructure and drive production-ready LLM experiences using Node.js, Next.js, and TypeScript. You'll own advanced prompt systems and complex LLM workflows with LangChain or LlamaIndex while leveraging Langfuse for observability and debugging. This role offers full ownership of AI features from experimentation to production.

🎯 What You'll Do

• Designing complex, dynamic prompt templates with conditional logic.
• Implementing structured outputs using JSON mode, function calling, or Zod/JSON schemas.
• Building evaluation pipelines with Langfuse for real-time response scoring.
• Debugging complex LLM chains to optimize cost, latency, and context usage.

📋 Requirements

• Node.js & Next.js deep knowledge for building reliable services.
• Dynamic prompting experience with context-dependent content.
• OpenRouter experience managing rate limits and cost-effective model selection.
• Langfuse or similar LLM observability tool experience.

✨ Nice to Have

• Fine-tuning models for domain tasks or JSON compliance.
• RAG architecture experience including indexing and retrieval.
• Basic Python for data science or AI evaluation scripts.

🎁 Benefits & Perks

• 🏡 Remote Work Environment freedom to work from anywhere.
• 🏖️ Unlimited PTO unlimited paid time off.
• 💻 Company-provided MacBook for seamless productivity.
• 📅 Paid National Holidays paid time off for holidays.

📨 Hiring Process

Estimated timeline: 2-4 weeks

1. 1Recruiter Screening· 40 min
2. 2First Interview· 60 min
3. 3Technical Interview· 45 min