What you'd do
- Build and lead the founding Jockey Core team through hiring,growth,and delivery.
- Own Jockey Core end-to-end roadmap from model selection through production scale-out.
- Lead critical serving and inference architecture decisions and set technical bar via design reviews.
What they want
- Track record leading hands-on ML or infrastructure teams,ideally founding or scaling small.
- Deep production experience serving and optimizing large-scale LLM inference at scale.
- Experience with batching,scheduling,quantization,disaggregated prefill,and speculative decoding.
Advertisement
Nice to have
- Experience with model compression including pruning,quantization-aware training,or distillation.
- Experience productionizing reasoning or agentic LLMs in live production environments.
- Experience with multi-region multi-cluster serving or large-scale GPU capacity planning.
Seoulstart's read
- Visa tier (likely)
- F-2 / F-4 / F-5 / F-6 holders welcome
- Korean language
- Korean not required
Related Seoulstart guides
Similar roles on Seoulstart
From Seoulstart