GenAI Inference Optimization Intern

NVIDIA Corporation; Warszawa; On-site; PLN 118,000 - 204,000; Full time

Benefits offered by this job

Competitive internship pay

Diversity & inclusion

Equal opportunity employer

Job summary

NVIDIA is seeking a GenAI Algorithms Intern in Warsaw to help optimize state‑of‑the‑art generative AI models. You will design, implement, and productionize model optimization algorithms for inference and deployment on NVIDIA hardware, focusing on efficiency and accuracy–performance tradeoffs.

Requirements include pursuing a Master’s or PhD in CS/AI, strong DL background, Python and PyTorch proficiency, and good communication skills.

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.
• Proficiency in Python, PyTorch, and modern ML frameworks/tools.
• Good written and verbal communication skills, with the ability to work both independently and collaboratively.

Responsibilities

• Design, implement, and productionize model optimization algorithms for inference and deployment.
• Develop modular, scalable software platforms for diverse AI models and techniques.
• Profile GPU kernels and optimize attention, KV cache, and parallelism on NVIDIA hardware.
• Collaborate across teams to integrate optimizations into NVIDIA's AI software stack.

Skills

Deep learning

Mastery of algorithms

Python programming

Communication skills

Education

Master's or PhD in CS/AI or related field

Tools

PyTorch

CUDA

vLLM

Hugging Face

Job description

NVIDIA is seeking a GenAI Algorithms Intern in Warsaw to help optimize state‑of‑the‑art generative AI models. You will design, implement, and productionize model optimization algorithms for inference and deployment on NVIDIA hardware, focusing on efficiency and accuracy–performance tradeoffs.

Requirements include pursuing a Master’s or PhD in CS/AI, strong DL background, Python and PyTorch proficiency, and good communication skills.