As the pioneers who introduced RISC-V to the world, SiFive is transforming the future of compute by bringing the limitless potential of RISC-V to the highest performance and most data-intensive applications in the world. SiFive’s unrivaled compute platforms are continuing to enable leading technology companies around the world to innovate, optimize and deliver the most advanced solutions of tomorrow across every market segment of chip design, including artificial intelligence, machine learning, automotive, data center, mobile, and consumer. With SiFive, the future of RISC-V has no limits.
At SiFive, we are always excited to connect with talented individuals, who are just as passionate about driving innovation and changing the world as we are.
Our constant innovation and ongoing success is down to our amazing teams of incredibly talented people, who collaborate and support each other to come up with truly groundbreaking ideas and solutions. Solutions that will have a huge impact on people's lives; making the world a better place, one processor at a time.
Are you ready?
To learn more about SiFive’s phenomenal success and to see why we have won the GSA’s prestigious Most Respected Private Company Award (for the fourth time!), check out our website and Glassdoor pages.
Job Description:
The Role:
Join the SiFive AI/ML Software Team to build the high-performance stack for Next-Gen AI. We are seeking engineers to optimize and deploy LLMs and Generative AI models on RISC-V architectures, spanning from compiler infrastructure to distributed runtime systems.
Responsibilities:
Compiler Infrastructure: Develop and maintain MLIR/IREE/Triton compiler stacks; optimize end-to-end (e2e) LLM performance and contribute to relevant open-source communities.
Runtime Systems: Design and implement single/multi-device scheduling and memory management layers; define hardware-software interfaces for high-throughput AI workloads.
Model Infrastructure: Implement model sharding and distribution strategies; lead the integration between high-level frameworks (e.g., PyTorch) and hardware backends.
Performance Optimization: Analyze and profile AI models to identify bottlenecks; develop high-performance kernels leveraging RISC-V Vector (RVV) and custom ISA extensions.
Co-design: Collaborate with hardware architects to influence the design of future AI accelerators and microarchitectures.
Requirements
Education: Master’s or PhD in Computer Science, Applied Mathematics, or a related field.
Programming: Strong proficiency in C++ and Python.
Domain Expertise: Solid understanding of AI/ML models (LLMs, Diffusion, Transformers) and their deployment challenges.
Technical Track (One or more of the following):
Experience with compiler frameworks like MLIR, IREE, LLVM, or Triton.
Background in system programming, memory management, or multi-device orchestration.
Knowledge of distributed computing, model parallelism, or tensor sharding.
Preferred Qualifications
Experience with AI/ML frameworks like PyTorch, ONNX Runtime, or TF/TFLite.
Familiarity with distributed training/inference and collective communications.
Active contributions to open-source AI/ML or compiler projects.
Experience in low-level performance tuning or MLPerf benchmarking.
If you want to do incredible work and be challenged by exciting, truly innovative projects that will test the boundaries of your skills and creativity, then SiFive is the place for you! Be proud of your work. Do things better. Join SiFive.
Additional Information:
This position requires a successful background and reference checks and satisfactory proof of your right to work in:
TaiwanAny offer of employment for this position is also contingent on the Company verifying that you are a authorized for access to export-controlled technology under applicable export control laws or, if you are not already authorized, our ability to successfully obtain any necessary export license(s) or other approvals.
SiFive is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees.