Design and develop Rebellions’ proprietary compiler stack to accelerate deep learning models on RBLN NPU products
Architect and implement production-grade frontend and backend compilers with strong generalization capabilities, covering broad functional requirements and optimization strategies
Evaluate and validate core-level and system-level functionalities in close collaboration with hardware and system software architects and engineers
Key Qualifications
Master’s degree or higher in Computer Science, Electrical Engineering, or a related field
Solid understanding of compiler architecture, including transformation passes, high/mid/low-level optimization and scheduling techniques, scratchpad and buffer memory allocation, and backend code generation
Strong analytical, troubleshooting, and debugging skills
Proficiency in C++ and Python
Ideal Qualifications
Demonstrated experience in developing and maintaining high-quality, production-level software systems
Experience with deep learning inference on specialized hardware platforms, including NPUs, GPUs, and mobile application processors
Expertise in cutting-edge LLM inference, with a strong understanding of advanced memory management and high-throughput generation techniques
Hands-on experience with parallel programming paradigms and the development of low-level kernels for AI accelerators or GPUs
Academic background in programming language, compiler, computer architecture is preferred
Design and develop Rebellions’ proprietary compiler stack to accelerate deep learning models on RBLN NPU products
Architect and implement production-grade frontend and backend compilers with strong generalization capabilities, covering broad functional requirements and optimization strategies
Evaluate and validate core-level and system-level functionalities in close collaboration with hardware and system software architects and engineers
Key Qualifications
Master’s degree or higher in Computer Science, Electrical Engineering, or a related field
Solid understanding of compiler architecture, including transformation passes, high/mid/low-level optimization and scheduling techniques, scratchpad and buffer memory allocation, and backend code generation
Strong analytical, troubleshooting, and debugging skills
Proficiency in C++ and Python
Ideal Qualifications
Demonstrated experience in developing and maintaining high-quality, production-level software systems
Experience with deep learning inference on specialized hardware platforms, including NPUs, GPUs, and mobile application processors
Expertise in cutting-edge LLM inference, with a strong understanding of advanced memory management and high-throughput generation techniques
Hands-on experience with parallel programming paradigms and the development of low-level kernels for AI accelerators or GPUs
Academic background in programming language, compiler, computer architecture is preferred