5+ years of experience in deep learning model implementation, software development, and performance optimization.
BSc, MS, or PhD in Computer Science, Computer Engineering, Electrical Engineering, Mathematics, Physics, or related field, or equivalent practical experience.
Proficiency in Python, with extensive hands-on experience in at least one major deep learning framework (e.g., PyTorch, TensorFlow, JAX).
Strong problem-solving and analytical skills, with a proven track record in debugging, performance tuning, and workload optimization.
Experience with deep learning compilers (e.g., PyTorch’s torch.compile, XLA, or similar technologies).
Nice to Haves
Experience with running large-scale workloads in HPC clusters.
Knowledge and passion for DevOps/MLOps practices for Deep Learning-based product development.
Solid understanding of Linux environments and containerization technologies such as Docker.
Familiarity with GPU programming or parallel computing.
What you'll be doing
Profile, analyze, and optimize the performance of deep learning models and workloads on ground-breaking hardware and software platforms.
Develop tooling for profiling and microbenchmarking of DL workloads running compiled models uncovering optimization opportunities.
Collaborate with teams across NVIDIA to provide performance insights and recommendations that improve the design and efficiency of DL frameworks and workloads.
Own the development and implementation of standard methodologies for compiling, testing, and deploying high-performance deep learning models.
Conduct performance benchmarking on enterprise-grade GPU clusters and pre-release hardware, driving improvements to NVIDIA’s DL software stack and hardware roadmap.
Perks and Benefits
An opportunity to craft hardware and software roadmaps at a leading AI company.
Work with world-class engineers on innovative deep learning models and high-performance technology.
Access to cutting-edge hardware shaping the future of AI.
An employer known for being one of the most desirable in the tech world, valuing creativity, autonomy, and diversity.