Software Engineer Kernel Programming Model
FuriosaAIVisit FuriosaAI website
FuriosaAI is a South Korean AI semiconductor company building energy-efficient inference accelerators, servers, and software for enterprise and cloud AI deployments.
Seoul, South Korea
Funding history
Investors
About FuriosaAI
FuriosaAI develops the RNGD AI inference accelerator and NXT RNGD Server, alongside a software toolchain for compiling, optimizing, and deploying LLM and agentic-AI workloads.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will design PyTorch-native integration layers and runtime environments for custom kernels. You will implement virtual ISA abstractions, build programming tools and reference implementations, and support a kernel development ecosystem.
Requirements
- Experience with systems programming in Rust, C++, or Go
- Understanding of computer architecture, including ISA, SIMD, and memory hierarchies
- Experience designing and building programming interfaces
- Bachelor's degree in Computer Science or a related technical field, or equivalent practical experience
- Knowledge of low-latency asynchronous execution, kernel optimization, or hardware-software co-design
- Knowledge of programming language theory and compiler infrastructure, including LLVM or MLIR
- Experience with developer communities, open source, technical evangelism, or developer ecosystems
Responsibilities
- Design integration layers and runtime environments for custom kernels in the PyTorch ecosystem
- Implement virtual ISA abstractions for direct hardware control and tensor-level programmability
- Build programming tools, technical specifications, and reference implementations for kernel development