Senior AI Engineer (Node.js/LLM)

TL;DR

Senior AI Engineer (Node.js/LLM): Shaping AI infrastructure and driving production-ready LLM experiences with an accent on advanced prompt systems, structured outputs, and complex LLM workflows. Focus on observability, debugging, evaluation, and data-driven decisions for model performance, reliability, and cost.

Location: Applicants from any country are welcome to apply for the position as long as they are located within approximately ± 4 hours of CET.

Company

hirify.global is a leading tech company that creates and operates innovative consumer products across health, education, and entertainment industries.

What you will do

• Shape AI infrastructure and drive production-ready LLM experiences.
• Own advanced prompt systems, structured outputs, and complex LLM workflows using LangChain or LlamaIndex.
• Implement various response schemes (JSON mode, function calling, Zod/JSON schemas) for predictable AI outputs.
• Build robust evaluation pipelines and use Langfuse to collect feedback and score response quality in real time.
• Perform deep debugging of complex LLM chains to identify bottlenecks and optimize for cost, latency, and context window usage.
• Run systematic AI A/B tests across different models and make deployment decisions strictly based on quantitative benchmarks.

Requirements

• Deep knowledge of Node.js & Next.js to build reliable services and handle complex LLM-generated data.
• Proven experience in building dynamic prompts with conditional logic and efficient context injection.
• Experience working with unified APIs like OpenRouter, managing rate limits, and selecting cost-effective models.
• Understanding of LLM observability principles, including tracing, test datasets, and integrating scoring systems (e.g., Langfuse).
• Experience with evaluation methodologies like RAGAS or building custom “LLM-as-a-judge” systems.
• Analytical mindset to transform raw generation logs into actionable business metrics and technical insights.
• English: B2 required.

Nice to have

• Practical experience in fine-tuning models for specific domain tasks or JSON compliance.
• Understanding of RAG Architecture, including indexing, retrieval, and re-ranking.
• Basic knowledge of Python for working with data science scripts or AI evaluation libraries.

Culture & Benefits

• Remote Work Environment promoting a healthy work-life balance.
• Enjoy unlimited paid time off (PTO) and paid national holidays.
• Receive a company-provided MacBook for seamless productivity.
• Benefit from a Flexible Independent Contractor Agreement offering autonomy and tax advantages.
• Be part of a fast-growing team with excellent opportunities for personal and professional growth.

Hiring process

• Recruiter Screening (40 minutes).
• Technical Interview (60 minutes).
• Final Interview (30 minutes).