Example listing with a fictional company — for demonstration only, not a live vacancy.
Job details
Overview
Nimbus Systems is looking for an AI Application Engineer to help embed large language model capability into its core product suite. You will work closely with backend and product teams to ship reliable, production-grade AI features — not just prototypes.
Responsibilities
- Design and build LLM-powered features using retrieval-augmented generation and structured prompting.
- Integrate third-party and open-source LLM APIs into existing backend services.
- Own the reliability, latency and cost profile of AI features in production.
- Collaborate with product and design on what AI capability should — and should not — do.
- Write evaluation suites to catch regressions in model behaviour before release.
Required Skills
Preferred Skills
AI Technology Stack
Interview Process
What to expect
Application Review
Initial review of your profile, projects and assessed skills.
Technical Screen
A conversation covering LLM engineering fundamentals and past project work.
Practical Exercise
Build a small RAG-based feature against a provided dataset.
Team Interview
Meet the engineering team and discuss the practical exercise in depth.
Ready to take the next step?
Applying connects you with the ITtoAI team — your verified profile and assessed skills go with you.
This is an example listing. Match scores and outcomes are illustrative and do not guarantee employment or hiring.