Software Engineer, Kernel Programming Model
About FuriosaAI
FuriosaAI builds high-performance, high-efficiency AI compute for the Inference Era. Founded in 2017 by veteran semiconductor and AI algorithm engineers, Furiosa operates globally with offices in Korea and Silicon Valley, along with a compiler-focused R&D lab in Lisbon.
Our vision is to make AI computing sustainable, enabling access to powerful AI for everyone on Earth. We solve the AI hardware energy and operational cost crisis at the architectural level, rather than through brute force, building the world's first truly AI-native compute platform to unlock the full potential of artificial intelligence for every enterprise.
Key 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.