LLM Inference Frameworks Engineer (GPU Acceleration)

Intel Corporation; Województwo pomorskie; Híbrido; PLN 216 000 - 388 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

Stock Program

Annual and Quarterly Bonuses

Employee Pension Plan

Medical Plan

Life insurance for you and your family

Ticket restaurant Card

Multisport Card

Resumo da oferta

Intel Poland is looking for a senior software engineer to design and optimize AI frameworks for LLM inference on Intel GPUs. You will contribute upstream to external open-source frameworks such as vLLM and PyTorch, writing and tuning compute kernels for attention, Mixture-of-Experts, and quantization.

You will collaborate across global teams to profile workloads, optimize data movement, and extend tests to ensure reliability as upstream evolves.

Qualificações

• Bachelor's degree in AI, Computer Science, Computer Engineering, Mathematics, Physics, or a related field.
• At least 2-3 years of relevant experience with a Bachelor's degree, or 1+ year with a Master's degree.
• Advanced expertise in Python programming.
• Demonstrated proficiency in PyTorch, including its internals or extension mechanisms.
• Hands-on experience with AI inference and large language models (LLMs).
• Strong problem-solving skills with experience in debugging and designing optimized software and algorithms.
• Proficiency in Linux environments from a user perspective.
• Solid foundation in AI frameworks, machine learning algorithms, and software engineering practices.

Responsabilidades

• Design, develop, and optimize AI framework software for LLM inference on Intel GPUs.
• Develop and optimize compute kernels (e.g., Triton, SYCL) for attention, Mixture-of-Experts, quantization, normalization.
• Implement and tune distributed execution paths in deep learning frameworks.
• Transform and optimize the computational-graph representation of neural networks.
• Profile inference workloads to identify bottlenecks and drive solutions with teams.
• Optimize code for multiple hardware backends considering memory hierarchy and ISA.
• Build and extend unit tests, correctness checks, and performance regression coverage.
• Collaborate with global teams and engage with the open-source community.

Conhecimentos

Python

PyTorch

LLMs

Linux

AI inference

Performance profiling

Debugging

Open source

Formação académica

Bachelor's degree in AI/CS/CE

Master's degree

Ferramentas

Triton

CUDA

SYCL

OpenCL

vLLM

Descrição da oferta de emprego

Intel Poland is looking for a senior software engineer to design and optimize AI frameworks for LLM inference on Intel GPUs. You will contribute upstream to external open-source frameworks such as vLLM and PyTorch, writing and tuning compute kernels for attention, Mixture-of-Experts, and quantization.

You will collaborate across global teams to profile workloads, optimize data movement, and extend tests to ensure reliability as upstream evolves.