GenAI Inference Optimization Intern

Sokoni Kwetu Limited; Polska; On-site; PLN 118,000 - 204,000; Full time

Job summary

NVIDIA is seeking a GenAI Algorithms Intern in Poland to help optimize state-of-the-art generative AI models and architectures. You will design, implement, and productionize model optimization algorithms across the AI software stack, focusing on efficiency, accuracy, and hardware co-design.

You will work with CUDA/Triton, PyTorch, and open-source frameworks, collaborating with teams to deploy optimized models and improve inference performance on NVIDIA hardware.

Qualifications

• 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.

Responsibilities

• Design, implement, and productionize model optimization algorithms for inference and deployment.
• Develop and integrate deep learning optimization algorithms into NVIDIA's AI software stack.
• Collaborate with teams on model optimization solutions for customer use cases.
• Conduct GPU kernel-level profiling to identify hardware and software optimization opportunities.

Skills

Deep learning

Language models

Python

PyTorch

Communication

Education

Master's or PhD in CS/AI/Applied Math

Tools

CUDA

Triton

Job description

NVIDIA is seeking a GenAI Algorithms Intern in Poland to help optimize state-of-the-art generative AI models and architectures. You will design, implement, and productionize model optimization algorithms across the AI software stack, focusing on efficiency, accuracy, and hardware co-design.

You will work with CUDA/Triton, PyTorch, and open-source frameworks, collaborating with teams to deploy optimized models and improve inference performance on NVIDIA hardware.