AI Platform Engineer: Scalable, Reliable LLM Workflows

Nostrion; Leusden; On-site; EUR 70,000 - 90,000; Full time

Benefits offered by this job

Competitive salary

Autonomy and impact

Job summary

Nostrion is seeking an AI Application Engineer to design and build scalable AI workflows and the orchestration layer that makes LLM functionality reliable across customer environments.

You will focus on prompt optimization, structured output control, model routing, evaluation logic, and production-ready workflows. You will collaborate with Platform Engineers and Product teams to scale capabilities while maintaining quality and cost efficiency.

Qualifications

• Experience building AI-powered applications and integrating LLMs into software products.
• Familiar with prompt design, output validation, workflow orchestration.
• Understanding of probabilistic systems and reliability considerations.
• Ability to operationalize AI with scalable, maintainable architectures.

Responsibilities

• Design and build scalable AI workflows reusable across customer environments.
• Develop the orchestration layer for reliable, production-ready LLM features.
• Focus on prompt optimization, output control, model routing, and evaluation.
• Contribute to evaluation frameworks for comparing prompts and model behavior.
• Collaborate with Platform Engineers, Product, and other AI Engineers to scale capabilities.

Skills

AI workflows

Prompt optimization

Model routing

Evaluation logic

Workflow orchestration

API integration

Python

Tools

Python backend

APIs

LLMs integration

Job description

Nostrion is seeking an AI Application Engineer to design and build scalable AI workflows and the orchestration layer that makes LLM functionality reliable across customer environments.

You will focus on prompt optimization, structured output control, model routing, evaluation logic, and production-ready workflows. You will collaborate with Platform Engineers and Product teams to scale capabilities while maintaining quality and cost efficiency.