AI Frameworks Engineer

Job Title

AI Frameworks Engineer

Role Summary

Join Intel's Data Center Group engineering team to develop and optimize large language model (LLM) inference frameworks and GPU kernel libraries. Work upstream in open-source projects (vLLM, PyTorch) to improve performance across the software and hardware stack.

Location: Gdansk, Poland. Hybrid work model.

Experience Level

Entry-level / Early Career. Guidance: 2–3 years relevant experience with a Bachelor's degree, or 1+ year with a Master's degree.

Responsibilities

Core responsibilities focus on framework and kernel development, performance tuning, and upstream contributions.

• Design, develop, and optimize AI framework software for LLM inference on Intel GPUs; contribute upstream to projects such as vLLM and PyTorch.
• Develop and optimize compute kernels (e.g., Triton, SYCL) for attention, MoE, quantization, normalization, and other transformer primitives.
• Implement and tune distributed execution paths: tensor/pipeline/data parallelism, collective communication, and async data movement.
• Transform and optimize computational graphs and implement ML primitives in math/kernel libraries.
• Profile inference workloads to identify bottlenecks across the stack and drive cross-team solutions.
• Adapt implementations to target hardware characteristics (memory hierarchy, instruction set, execution model).
• Build unit tests, correctness checks, and performance regression coverage to maintain upstream stability.
• Collaborate with framework, compiler, and ML engineers globally and participate in open-source code review and discussion.

Requirements

Must-have technical skills and relevant experience. Preferred skills listed separately.

• Must-have: Advanced Python programming skills.
• Must-have: Proficiency with PyTorch, including internals or extension mechanisms.
• Must-have: Hands-on experience with AI inference and large language models (LLMs).
• Must-have: Strong debugging and problem-solving skills; experience designing optimized software and algorithms.
• Must-have: Comfortable in Linux user environments and strong software engineering practices.
• Must-have: Experience profiling inference workloads and addressing performance bottlenecks.
• Must-have: Familiarity with distributed execution concepts (tensor/pipeline/data parallelism) and collective communication.
• Preferred: Experience writing or optimizing GPU compute kernels (Triton, CUDA, SYCL, OpenCL, or similar).
• Preferred: Experience reading and interpreting hardware-level performance profiles and performing optimizations for AI workloads.
• Preferred: Familiarity with vLLM or other LLM serving frameworks, contributions to major open-source AI projects, and understanding of numerical precision/quantization formats (FP8, INT8, INT4).

Education Requirements

Bachelor's degree in AI, Computer Science, Computer Engineering, Mathematics, Physics, or a related field. The posting also provides guidance that 2–3 years of relevant experience is expected with a Bachelor's degree, or 1+ year with a Master's degree. No certifications were specified.

About the Company

Company: Intel Corporation

Headquarters: Santa Clara, California, USA

Intel Corporation is a leading multinational technology company known for its innovative semiconductor solutions, including microprocessors, artificial intelligence accelerators, and memory products. Headquartered in the United States, Intel focuses on cutting-edge technology and a collaborative working environment, driving advancements in semiconductor manufacturing to meet global demands. The company emphasizes professional development and aims to shape the future of technology through groundbreaking designs.