Synopsys - Staff/Senior Staff GPU Engineer (5-10 yrs)

Job Overview :

We are seeking an experienced and highly skilled Staff/Senior Staff GPU Engineer to join our team, focusing on optimizing and implementing GPU-accelerated algorithms for Optical Proximity Correction (OPC) software in the Electronic Design Automation (EDA) industry.

As part of our dynamic engineering team, you will play a key role in designing and optimizing cutting-edge algorithms for high-performance computing systems that enable efficient large-scale geometric data handling.

This is a senior-level role that requires a deep understanding of GPU hardware, parallel computing, and algorithmic optimization.

You will collaborate closely with cross-functional teams to deliver innovative solutions and ensure the integration of GPU-accelerated functionalities into our existing systems.

Key Responsibilities :

- Lead the optimization of existing GPU implementations for OPC software to maximize efficiency, scalability, and performance across large-scale datasets.

- Develop new GPU-accelerated algorithms to handle complex geometric data and accelerate critical components of the OPC flow.

- Focus on improving throughput, latency, and resource utilization for GPU-intensive tasks related to EDA tools.

- Research and design novel GPU-accelerated algorithms tailored to address the specific needs of the OPC process, including handling of massive geometric data, numerical methods, and simulation techniques.

- Optimize memory usage and computational efficiency for real-time data processing, with a focus on reducing overhead while ensuring accuracy.

- Stay updated with the latest advancements in GPU technology, CUDA/OpenCL programming models, and the overall field of high-performance computing (HPC).

- Investigate new GPU architectures, software libraries, and tools to enhance the capabilities of the OPC software.

- Provide recommendations for adopting emerging technologies and integrating them into the product stack.

- 5-10 years of experience working with GPU-accelerated systems and in-depth knowledge of GPU programming, particularly with technologies such as CUDA, OpenCL, and ROCm.

- Proven track record of delivering high-performance GPU implementations for complex applications, with a focus on optimizing large-scale, data-intensive processes.

- Expertise in parallel programming, memory management, and optimization techniques for GPU platforms.

- Strong proficiency in C++, Python, and experience with distributed computing environments.

- Experience with profiling, debugging, and optimizing GPU code using tools like NVIDIA Nsight, CUDA Profiler, and others.

- Familiarity with high-performance computing (HPC) clusters and related technologies (e.g, MPI, distributed systems, multi-threading).

- Experience in using relevant GPU libraries and frameworks such as cuBLAS, cuFFT, and Thrust