Software Engineer, Compiler (Kernel Optimization)
FuriosaAI · Seoul, South Korea
Infrastructureonsite
At a glance
Highlights
- Own performance of critical AI kernels integrated into Furiosa-LLM serving.
- Tackle dynamic serving workloads with scheduling and specialization techniques.
- Ship optimized kernels on RNGD silicon running live enterprise workloads.
Ideal candidate
Low-level performance enthusiast who loves profiling bottlenecks and squeezing efficiency from parallel hardware. Excited by full-stack co-design and shipping production kernels for LLM serving.
Requirements
- BS in Computer Science, AI, Electrical Engineering or related field
- Experience developing low-level or performance-critical software
- Experience analyzing bottlenecks with profiling, benchmarking and hardware performance data
- Understanding of parallel computation, memory hierarchies and data movement
Lab profile
About FuriosaAI
Builds high-performance, high-efficiency AI compute for the Inference Era.
What they build
- AI inference accelerators
- High-efficiency AI compute hardware
Known for
- Energy-efficient AI chip architecture
- High-performance AI inference
- AI compiler development
Key facts
- Founded in 2017
- Offices in Korea and Silicon Valley
- Compiler-focused R&D lab in Lisbon
Posted · Last seen