GenAI Model Optimization Intern — Inference & Efficiency

NVIDIA Corporation; Województwo mazowieckie; Presencial; PLN 118.000 - 204.000; Jornada completa

Descripción de la vacante

NVIDIA Corporation in Poland is seeking a GenAI Algorithms Intern to design, implement, and productionize model optimization algorithms for inference on NVIDIA hardware. You will work on modular platforms and contribute APIs to optimize LLMs, VLMs, and diffusion models.

You will gain hands-on experience with quantization, pruning, and neural architecture search while collaborating with cross-functional teams in a fast-paced environment.

Formación

• Pursuing advanced degree in CS/AI with strong ML foundation.
• Hands-on experience with language models and PyTorch.
• Strong algorithms and programming skills.

Responsabilidades

• Design and implement model optimization algorithms for inference.
• Deploy optimized models within NVIDIA AI software stack.
• Profile GPU kernels and optimize attention kernels and KV cache.
• Collaborate with teams on customer use cases.

Conocimientos

Python

PyTorch

Deep learning

Language models

Algorithms

Educación

Master's or PhD in CS/AI

Herramientas

vLLM

JAX

SGLang

NVIDIA Model Optimizer

Descripción del empleo

NVIDIA Corporation in Poland is seeking a GenAI Algorithms Intern to design, implement, and productionize model optimization algorithms for inference on NVIDIA hardware. You will work on modular platforms and contribute APIs to optimize LLMs, VLMs, and diffusion models.

You will gain hands-on experience with quantization, pruning, and neural architecture search while collaborating with cross-functional teams in a fast-paced environment.