GenAI Algorithms Intern – Model Optimization for Inference

117.8k - 204.1k PLN117 750 - 204 100 PLN/ rok./ rok.StażUmowa o staż

InternZdalnie·WarszawaFull-time·Umowa o staż

#463057·Dodano 5 dni temu·26

Źródło: NVIDIA

Aplikuj teraz

Tech Stack / Keywords

Python PyTorchNVIDIA Model OptimizerTensorRT-LLMCUDATritonvLLMSGLangNeMoHugging Face

Podsumowanie oferty

As part of NVIDIA’s Algorithmic Model Optimization Team, you will design, implement, and productionize algorithms that optimize generative AI models for inference and deployment on NVIDIA hardware. The work spans the AI software stack, including Model Optimizer, NeMo/Megatron, TensorRT-LLM, PyTorch, Hugging Face, vLLM, and SGLang, with opportunities for GPU kernel optimization using CUDA and Triton.

Wymagania

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 ML frameworks and tools.
Good written and verbal communication skills, and ability to work independently and collaboratively in a fast-paced environment.

Nice to have:

Experience with model optimization and efficiency, such as quantization, distillation, or pruning.
Contributions to PyTorch, JAX, vLLM, SGLang, or other machine learning training and inference frameworks.
Hands-on experience training or fine-tuning generative AI models on large-scale GPU clusters.
Knowledge of GPU architectures and compilation stacks, and ability to analyze and debug end-to-end performance.
Familiarity with NVIDIA’s deep learning SDKs, including Model Optimizer and NeMo.

Obowiązki

Help design and build modular, scalable model optimization software platforms for diverse AI models and optimization techniques.
Explore, develop, and integrate deep learning optimization algorithms, including quantization, speculative decoding, sparsity, distillation, pruning, and neural architecture search, into NVIDIA’s AI software stack.
Deploy optimized models into open-source inference frameworks and contribute specialized APIs, model-level optimizations, and features for the latest NVIDIA hardware.
Collaborate with NVIDIA teams on model optimization solutions for customer use cases and end-to-end workflows, balancing accuracy and performance.
Profile GPU kernels to identify hardware and software optimization opportunities, including efficient attention kernels, KV cache optimization, and parallelism strategies.

NVIDIA

20 aktywnych ofert

Zobacz wszystkie oferty

Aplikuj teraz