Senior Software Engineer, Algorithms and Libraries of AI/ML/DSP

Job Title

Senior Software Engineer, Algorithms and Libraries of AI/ML/DSP

Role Summary

Develop and optimize high-performance algorithms and libraries for RISC-V vector processors, deploy them into AI/ML and DSP frameworks, and collaborate with compiler, runtime, and hardware teams to integrate and productize solutions.

Position is based in Hsinchu, Taiwan; candidates must be authorized to work in Taiwan.

Experience Level

Senior — typically 3+ years of practical experience developing and optimizing algorithms for microarchitectures.

Responsibilities

The role focuses on library development, framework integration, and cross-functional co-design.

• Design and implement high-performance algorithms and software libraries for RISC-V, leveraging vector processing and custom ISA extensions.
• Deploy and integrate SiFive kernel libraries into open-source AI/ML and DSP frameworks and inference runtimes.
• Collaborate with compiler and runtime engineers to improve optimizations and integrate algorithms into an MLIR-based parallel programming framework.
• Participate in hardware-software codesign with architects and hardware engineers to balance microarchitecture and algorithm tradeoffs.
• Lead cross-functional projects from conception through product release, including debugging, testing, and performance analysis.

Requirements

Must-have skills and experience:

• 3+ years practical experience developing and optimizing algorithms for specific microarchitectures; experience writing low-level C and assembly.
• Theoretical knowledge in algorithms analysis, linear algebra, and parallel computing.
• Proficiency in C/C++, Python, build systems and templating (CMake, Jinja2) for development, debugging, testing, and performance analysis.
• Familiarity with major ML training frameworks (TensorFlow, PyTorch) and inference runtimes (ONNX Runtime, TVM, LiteRT, ExecuTorch, or similar).

Nice-to-have:

• Experience with ARM SIMD technologies (NEON/MVE) or DSP extensions.
• Familiarity with parallel computing frameworks such as CUDA or OpenMP.

Education Requirements

Master's or PhD in Computer Science, Applied Mathematics, or a related field.

About the Company

Company: SiFive

Headquarters: San Mateo, California, United States

SiFive is a pioneering company in the RISC-V ecosystem, focused on transforming the future of computing by delivering high-performance, data-intensive RISC-V solutions. Their compute platforms empower leading technology firms to innovate across various markets, including AI, machine learning, and automotive sectors. SiFive is recognized for its commitment to ongoing innovation and fostering collaboration among talented teams, impacting lives by enabling advanced chip design.