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.
FriendliAI
Software Engineer – AI Inference Engine
Seoul, Seoul, South KoreaPosted 3 months agofulltime
What you'd do
- Design and optimize custom GPU kernels for transformer and diffusion AI workloads
- Contribute to kernel compiler,memory planner,runtime,and other core inference engine components
- Analyze performance bottlenecks across the software and hardware stack and implement optimizations
What they want
- 5+ years experience in production or high-impact research environments
- Production-level expertise in Python and C++ for systems-level engineering work
- Hands-on experience writing,optimizing,and profiling GPU kernels in production
Nice to have
- Experience developing ML compilers or code generation and kernel fusion systems
- Understanding of multi-GPU and distributed inference strategies at scale
Seoulstart's read
- Visa tier (likely)
- E-7 specialty / professional (likely)
- Korean language
- Korean not required
- English friendliness
- High: JD in English, foreign-friendly signals