This role may have closed.
Listings older than 30 days are deprioritized in search. The link to the source is still below in case the posting is still open. For active openings, see similar jobs.
Upstage
AI Engineer - LLM Serving Platform
Seoul, South KoreaPosted 3 months ago
What you'd do
- Design,develop,and operate LLM serving platform on large-scale GPU clusters.
- Implement routing and scheduling logic to handle large-scale traffic efficiently.
- Implement custom extensions for open-source inference runtimes like vLLM and SGLang.
What they want
- 3+ years of AI model serving experience.
- Deep understanding of latest LLM architectures and serving techniques.
- Production experience developing and operating real-time AI inference services.
Nice to have
- Multi-region global service operations experience.
- Contributions to open-source LLM frameworks (vLLM,SGLang,TensorRT-LLM,Transformers).
- Large-scale GPU cluster operations experience.
Seoulstart's read
- Visa tier (likely)
- E-7 specialty / professional (likely)
- Korean language
- Business-level Korean required
- English friendliness
- Medium: English JD, mixed-language workplace