Software Engineer, Kernel Programming Model

Company: furiosa-ai

Location: Seoul HQ

Type: full_time

Posted: Aug 18, 2026

✨ AI Summary

FuriosaAI, a company building AI accelerators and NPU hardware, is hiring a Software Engineer for its Kernel Programming Model team at its Seoul HQ. The role focuses on designing PyTorch-native kernel integration, virtual ISA abstractions, and developer tools, using systems programming languages like Rust, C++, or Go. Requires a Bachelor's in CS or equivalent, deep computer architecture knowledge (ISA, SIMD, memory hierarchies), and experience building programming interfaces. Preferred qualifications include advanced degrees, compiler infrastructure experience (LLVM/MLIR), and open-source community engagement; no salary or remote policy mentioned.

Responsibilities

PyTorch-Native Kernel Programming Model: Design the integration layer and runtime environments that enable custom kernels to execute as native extensions within the PyTorch ecosystem.
Virtual ISA: Implement architectural abstractions that resolve performance bottlenecks through direct hardware control while maintaining tensor-level programmability.
Kernel Developer Ecosystem: Build core programming tools, technical specifications, and reference implementations to enable seamless kernel development and community contributions.

Minimum Qualifications

Bachelor’s degree in Computer Science or a related technical field, or equivalent practical experience.
Experience in systems programming such as Rust, C++, or Go with a deep understanding of computer architecture, including ISA, SIMD, and memory hierarchies.
Experience in designing and building clean, robust, and well-defined programming interfaces.

Preferred Qualifications

Master’s or PhD degree in Computer Science or a related technical field, or equivalent practical experience.
Experience in designing low-latency asynchronous execution models, kernel-level performance optimizations, or hardware-software co-design.
Experience in programming language theory and compiler infrastructure, including the design of domain-specific languages or intermediate representations using frameworks such as LLVM or MLIR.
Experience in engaging the developer community through open-source contributions, technical evangelism, or managing developer ecosystems.