Performing functional verification and debugging focusing on enhancing the stability of RBLN SDK
Performing device profiling and optimization focusing on enhancing the performance of RBLN SDK
Designing internal/external SDK verification utilities, including performance profiler/debugger, model partitioning/feeding frameworks, etc.
Key Qualifications
Bachelor's or Master's degree in Computer Science, Electrical Engineering, or a related field
Thorough knowledge of deep learning models for various applications, including vision, language, speech, etc.
Familiarity with system software, including compiler, runtime, driver, firmware, etc.
Proficiency in programming languages: Python, C++
Ideal Qualifications
Experience in converting models for deployment on specific hardware, such as TF/PyTorch to ONNX, ONNX to TensorRT/OpenVINO, TF to TFLite, etc.
Experience in porting and accelerating deep learning models on specific hardware, including x86 CPUs with SSE/AVX instructions, ARM CPUs with NEON instructions, heterogeneous computing on SoCs with CPU, GPU, NPU, and DSP, etc.
채용 및 업무 수행과 관련하여 요구되는 법령 상 자격이 갖추어지지 않은 경우 채용이 제한될 수 있습니다.
보훈 대상자 및 장애인 여부는 채용 과정에서 어떠한 불이익도 미치지 않습니다.
담당 업무 범위는 후보자의 전반적인 경력과 경험 등 제반사정을 고려하여 변경될 수 있습니다. 이러한 변경이 필요할 경우, 최종 합격 통지 전 적절한 시기에 후보자와 커뮤니케이션 될 예정입니다.
공유하기
NPU SDK Software Engineer
Responsibilities and Opportunities
Performing functional verification and debugging focusing on enhancing the stability of RBLN SDK
Performing device profiling and optimization focusing on enhancing the performance of RBLN SDK
Designing internal/external SDK verification utilities, including performance profiler/debugger, model partitioning/feeding frameworks, etc.
Key Qualifications
Bachelor's or Master's degree in Computer Science, Electrical Engineering, or a related field
Thorough knowledge of deep learning models for various applications, including vision, language, speech, etc.
Familiarity with system software, including compiler, runtime, driver, firmware, etc.
Proficiency in programming languages: Python, C++
Ideal Qualifications
Experience in converting models for deployment on specific hardware, such as TF/PyTorch to ONNX, ONNX to TensorRT/OpenVINO, TF to TFLite, etc.
Experience in porting and accelerating deep learning models on specific hardware, including x86 CPUs with SSE/AVX instructions, ARM CPUs with NEON instructions, heterogeneous computing on SoCs with CPU, GPU, NPU, and DSP, etc.