Research · Seoul / Remote
AI Research Engineer
Take language and generation models from paper to product, reliable enough to put in front of marketers.
You sit between research and engineering. You read the papers, run the experiments, and then ship the parts that actually move a metric for our users.
Our agents plan campaigns, generate content, and report on outcomes. Your job is to make each of those steps measurably better and cheaper over time.
What you'll do
- Prototype, evaluate, and productionize model driven features across our products.
- Build evaluation harnesses so every change is judged on real, measurable outcomes.
- Own prompt design, retrieval, and orchestration for our agent workflows.
- Keep an eye on cost and latency, and drive both down without losing quality.
What we look for
- Strong applied ML background with hands on experience shipping model driven features.
- Fluency in Python and comfort wiring models into a TypeScript product.
- A rigorous, experiment first mindset and a habit of measuring what matters.
- Clear writing, because research only counts once someone else can use it.
Interested in this role?
Tell us a bit about yourself and we'll be in touch.