Senior Deep Learning Software Engineer, Algorithmic Model Optimization

We are now seeking a Senior Deep Learning Software Engineer for Algorithmic Model Optimization! Join our team of experts in algorithmic model optimization and help unleash the enormous potential of AI with generative models such as large language models (LLM) and diffusion models. As a Senior Deep Learning Software Engineer, you will be at the forefront of pushing the boundaries of these models and enabling their deployment on a larger scale with unmatched efficiency. We are developing a groundbreaking software platform that will not only be utilized internally but will also have a significant external impact by enabling the creation of revolutionary AI products. This is a unique opportunity for passionate software engineers with a strong background in Deep Learning to join us in solving the most significant challenges in the field. Your role will be critical in our mission to maximize the potential of our rapidly expanding data center deployments. Additionally, you will play a crucial role in adopting a data-driven approach to hardware design and system software development. Collaboration is at our core, and you will get the opportunity to work closely with a diverse range of teams at NVIDIA, including Applied Deep Learning Research teams, CUDA Kernel and DL Framework development teams, and the Silicon Architecture Team. In this position, you will engage actively with internal stakeholders, users, and members of the open-source community. Your contribution will be vital in defining and implementing innovative model optimization algorithms. Your work will include researching and developing highly efficient search algorithms, defining public APIs, implementation, and various other software engineering tasks. We are seeking individuals who are as enthusiastic as we are about pushing the limits of AI and contributing to groundbreaking advancements in the field. If you're passionate about innovation, tackling complex DL problems, and working in a collaborative environment, this is the perfect opportunity for you. Join us, and together, we'll shape the future of AI model optimization and its impact on the world. What you’ll be doing: - Prototype and develop model optimization methods, and build an impactful model optimization platform. - Collaborate with internal and external partners to accelerate the adoption of deep learning model optimization. - Stay up to date with the latest research and innovations in generative AI and model optimization techniques. - Analyze and optimize the theoretical and practical performance of DL models generated. - Publish findings in top AI conferences and create Intellectual Property. What we need to see: - Masters, PhD, or equivalent experience in Computer Science, AI, Applied Math, or related field. - 10+ years of relevant work or research experience in Deep Learning. - Excellent software design skills, including debugging, performance analysis, and test design. - Strong algorithms and programming fundamentals. - Ability to work independently, define project goals and scope, and lead your own development effort. - Good communication, documentation habits, and interpersonal skills. - Experience with one or more: Python, C++, performance tuning. Ways to stand out from the crowd: - Contributions to PyTorch, JAX, or other Machine Learning Frameworks. - Knowledge of GPU architecture and compilation stack, with the ability to understand and debug end-to-end performance. - Familiarity with Nvidia’s deep learning SDK such as TensorRT. - Strong understanding of deep learning algorithms and solutions. - Strong understanding of ML model optimization techniques such as quantization, pruning, distillation. Increasingly known as “the AI computing company” and widely considered one of the most desirable employers in the technology world, NVIDIA offers highly competitive salaries and a comprehensive benefits package. Are you creative, motivated, and love a challenge? If so, we want to hear from you! Come, join our model optimization group, where you can help build real-time, cost-effective computing platforms driving our success in this exciting and rapidly growing field. The base salary range is 216,000 USD - 414,000 USD. Your base salary will be determined based on your location, experience, and the pay of employees in similar positions. You will also be eligible for equity and benefits.