Senior Software Engineer – AI/ML Heterogeneous Systems

About the role

Join SiFive’s AI/ML Software Team to build a high‑performance stack for next‑generation AI on RISC‑V architectures. You will work on optimizing and deploying large language models and generative AI across heterogeneous hardware.

Key responsibilities

• Design and implement the core compute programming model, device runtime daemon, and asynchronous task orchestration.
• Lead integration of production‑grade inference stacks such as vLLM and SGLang on RISC‑V, optimizing memory‑bound operations and KV‑cache management.
• Enable seamless lowering from Triton/MLIR‑based compilers to SiFive hardware extensions and develop high‑performance kernels for RVV and matrix units.
• Collaborate with hardware architects to co‑design future AI accelerators and micro‑architectures.

Required profile

• At least 3 years of relevant industry experience.
• MS/PhD in Computer Science, Electrical Engineering or related field.
• Strong proficiency in C++ and Python.
• Deep understanding of heterogeneous computing models (CUDA, ROCm, OpenCL concepts).

Required skills

• C++
• Python
• CUDA C++
• RISC‑V Vector (RVV) extensions
• Triton / MLIR compiler experience
• vLLM, SGLang, or TGI inference frameworks
• Experience with open‑source AI projects (e.g., PyTorch, LLVM/MLIR)