21 hours ago
Zürich, SwitzerlandIntern
Responsibilities
- Design and build modular, scalable model optimization software platforms for diverse AI models and optimization techniques.
- Develop and integrate generative AI optimization algorithms, including quantization, speculative decoding, sparsity, distillation, pruning, and neural architecture search.
- Deploy optimized models into inference frameworks and contribute APIs, model-level optimizations, and hardware-focused features.
- Collaborate on model optimization solutions for customer use cases and improve end-to-end accuracy and performance trade-offs.
- Profile GPU kernels and identify optimization opportunities involving attention kernels, KV cache optimization, and parallelism strategies.
Requirements
- Pursuing a master’s or PhD in Computer Science, AI, Applied Math, or a related field.
- Strong deep learning background and hands-on experience with language models.
- Solid foundation in algorithms and programming.
- Proficiency in Python, PyTorch, and modern machine learning frameworks and tools.
- Strong written and verbal communication skills and ability to work independently and collaboratively.
- Preferred: experience with quantization, distillation, pruning, or other model-efficiency techniques.
- Preferred: contributions to PyTorch, JAX, vLLM, SGLang, or other machine learning training and inference frameworks.
- Preferred: experience training or fine-tuning generative AI models on large-scale GPU clusters.
- Preferred: knowledge of GPU architectures, compilation stacks, and end-to-end performance analysis and debugging.
- Preferred: familiarity with NVIDIA Model Optimizer and NeMo.
Benefits
- NVIDIA offers highly competitive salaries and a comprehensive benefits package.
- NVIDIA is committed to a diverse work environment and is an equal opportunity employer.
Categories
About Nvidia
Nvidia designs and sells GPUs and accelerated computing platforms for data centers, AI/ML, graphics, gaming, and automotive, monetizing through hardware, software platforms (CUDA, AI frameworks), and systems like DGX and networking. Customers include cloud providers, enterprises, researchers, and OEMs. Founded in 1993 and headquartered in Santa Clara, it is a public company traded on NASDAQ under NVDA.