Software Engineer, Deep Learning cuDNN - New College Graduate 2023

  • Full Time
Job expired!
Do you enjoy coding swiftly and creating software structures to tackle intricate challenges? We're searching for diligent software engineers to collaborate in designing, constructing, and deploying cuDNN: our GPU-boosted library of primitives for deep neural networks. Artificially intelligent machines, equipped with AI computers that can learn, reason and connect with humans, are now a reality, not mere science fiction. It's a phenomenal time indeed. The AI era has dawned, and we're the driving force behind it. If this role aligns with your abilities and interests, share why you believe you'd be an excellent fit for our team, and we'd be thrilled to tell you more about our work! What you'll be doing: - Designing commercial-grade software that's launched as a part of NVIDIA's AI software suite, including the streamlined support for large language model (LLM). - Examining the functioning of significant workloads, enhancing our current software, and suggesting improvements for future software. - Collaborating with intersecting teams of deep learning software engineers and GPU architects to innovate across domains like generative AI, self-driving vehicles, computer vision, and recommendation systems. - Keeping pace with the continually transforming AI industry by staying versatile and eager to contribute across the entire codebase, including API design, software structure, performance modeling, testing, and GPU kernel development. What we'd like to see: - B.S. or higher degree in computer science (or similar) or relevant experience - Robust programming abilities in C/C++ development and familiarity with Python. - A solid comprehension of linear algebra. - Familiarity with the latest tendencies in machine learning. - Outstanding problem-solving skills, including the application of algorithms and data structures. - Experience with performance assessment, profiling, and code optimization. Ways to distinguish yourself from the crowd: - Expertise in GPU programming and optimization (e.g., CUDA or OpenCL). - Practical exposure to machine learning, especially deep learning. - Familiarity with computer architecture and building performance models for CPUs, GPUs, or other accelerators. - Profound experience with data science, statistical analysis, and visualization. - Past work on large complex codebases collaborating with multiple developers, primarily libraries, compilers, or system software.