hotskills.tech

About Job

Role : CUDA Software Engineer Opening : 1 Experience : 2+ years About The Role We are looking for a passionate CUDA Engineer to develop and optimize high-performance computing libraries and applications. You will work on cutting-edge machine learning, computer vision, and numeric algorithm implementations, ensuring they are highly efficient on GPUs and other hardware accelerators. Key Responsibilities • Design, implement, and optimize parallel algorithms using CUDA and C++ for GPUs and other target platforms. • Collaborate with software and hardware teams to maximize performance on CPUs, GPUs, DSPs, and accelerators. • Apply low-level optimizations including parallelization, memory management, vectorization, and efficient data movement. • Build performance benchmarks, run profiling and analysis, and fine-tune implementations to meet performance goals. • Understand customer requirements and deliver optimized solutions tailored to their needs. • Stay updated with the latest advancements in CUDA programming, GPU architectures, and optimization techniques. Qualifications • Bachelors or Masters degree in Computer Science, Information Technology, Electronics & Communication, or a related field. • 2+ years of hands-on experience in CUDA development and GPU programming. • Proficiency in C/C++ programming and experience with CUDA, OpenCL, or similar parallel computing technologies. • Good understanding of GPU architecture, memory hierarchies, and multi-threaded programming concepts. • Familiarity with performance profiling tools (like NVIDIA Nsight, Visual Profiler, etc.). • Experience with machine learning, computer vision, or high-performance numeric computing (preferred but not mandatory). • Strong analytical, debugging, and problem-solving skills. • Ability to work independently and collaborate in a fast-paced team environment. Bonus Points (Good To Have) • Exposure to deep learning frameworks (TensorFlow, PyTorch, etc.). • Experience in optimizing algorithms for low latency and high throughput. • Knowledge of SIMD instructions and cache optimization strategies. (ref:hirist.tech) job perk: Posted At: 23 hours ago, job perk: Schedule Type: Full-time