17 часов назад
AI/ML Software Engineer
Вакансия из Hirify Global, списка международных tech-компанийДля мэтча и отклика нужен Plus
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
AI/ML Software Engineer (RISC-V/LLMs): Building and optimizing the high-performance software stack for deploying LLMs and generative AI models on RISC-V architectures with an accent on compiler infrastructure, distributed runtime systems, model sharding, and hardware-software co-design. Focus on profiling AI workloads, developing high-performance RVV kernels, designing multi-device scheduling and memory management, and integrating frameworks such as PyTorch with hardware backends.
Location: Hsinchu, Taiwan. Full-time onsite position. Candidates must provide satisfactory proof of the right to work in Taiwan and be authorized to access export-controlled technology, or must be able to obtain the required export licenses or approvals.
Company
develops high-performance RISC-V compute platforms for artificial intelligence, machine learning, automotive, data center, mobile, and consumer applications.
What you will do
- Develop and maintain MLIR, IREE, and Triton compiler stacks while optimizing end-to-end LLM performance.
- Design single-device and multi-device scheduling and memory-management layers for high-throughput AI workloads.
- Implement model sharding and distribution strategies and integrate PyTorch and other high-level frameworks with hardware backends.
- Profile AI models, identify bottlenecks, and develop high-performance kernels using RISC-V Vector extensions and custom ISA extensions.
- Collaborate with hardware architects on future AI accelerators and microarchitectures.
- Contribute to relevant open-source compiler and AI/ML projects.
Requirements
- Master’s or PhD in Computer Science, Applied Mathematics, or a related field.
- Strong proficiency in C++ and Python.
- Solid understanding of LLMs, diffusion models, transformers, and AI/ML deployment challenges.
- Experience with MLIR, IREE, LLVM, Triton, system programming, memory management, or multi-device orchestration.
- Knowledge of distributed computing, model parallelism, or tensor sharding.
- Right to work in Taiwan and authorization to access export-controlled technology are required.
Nice to have
- Experience with PyTorch, ONNX Runtime, or TF/TFLite.
- Experience with distributed training or inference and collective communications.
- Contributions to open-source AI/ML or compiler projects.
- Experience with low-level performance tuning or MLPerf benchmarking.
Culture & Benefits
- Collaborative engineering environment focused on innovation in RISC-V computing.
- Opportunities to work on next-generation AI accelerators and high-performance compute systems.
- Inclusive workplace committed to diversity and equal employment opportunity.
- Employment is contingent on successful background and reference checks.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →