The Role and Impact
Intel is building the open software stack that makes large language models run fast on Intel GPUs. You will join the engineering team that develops and optimizes LLM inference frameworks - working directly in vLLM and in the SW stack beneath it and in the upstream. You will write and tune compute kernels, reshape execution paths, hunt performance bottlenecks and submit your changes into widely used open-source projects. If you want to optimize how fast AI workloads run, this is that role.
Business group
The Data Center Group (DCG) is at the forefront of delivering cutting-edge technologies to power the world's data centers, enabling advanced computing solutions that drive innovation across industries. Within this group, our team is dedicated to developing AI frameworks and workloads that empower researchers and developers to create high-performance, scalable solutions for complex AI challenges. We aim to build tools and technologies that accelerate progress in AI, aligning with Intel's mission to advance global technology.
Key Responsibilities
- Design, develop, and optimize AI framework software for LLM inference on Intel GPUs, contributing upstream to external open-source frameworks such as vLLM and PyTorch.
- Develop and optimize compute kernels for transformer inference.
- Implement and tune distributed execution paths - tensor, pipeline, and data parallelism, collective communication, and asynchronous data movement within deep learning frameworks.
- Transform and optimize the computational-graph representation of neural network models, and develop machine learning primitives in mathematical and kernel libraries.
- Profile inference workloads to identify performance bottlenecks across the stack, quantify them, and propose and drive solutions together with the individual component teams that own each layer.
- Optimize code for a range of computing hardware backends, adapting implementations to the memory hierarchy, instruction set, and execution model of each target.
- Build and extend unit tests, correctness checks, and performance regression coverage so that framework and kernel work stays reliable as upstream moves.
- Collaborate with framework, compiler, and machine learning engineers across global teams, and engage with the open-source community through code review and technical discussion.
At Intel, employees share in successes, enjoy comprehensive rewards and are inspired by an innovative & inclusive workplace. What can you expect when there is a match between us?
- We guarantee you will be working in a safe environment; either at your own home or in our premises if needed, the security and wellbeing of you and your family stands as our utmost responsibility.
- You will have constant opportunities to develop your professional career through technical and soft skills training, taking part in innovation projects or rotational programs
- Flexible working hours are important to us
- And our Amazing Benefits to make life easier and more enjoyable are waiting for you: Stock Program, Annual and Quarterly Bonuses, Employee Pension Plan, Medical Plan and life insurance for you and your Family, Peer to peer recognition, Ticket restaurant Card, Multisport Card / Holiday card, Groups of enthusiasts, Exclusive employee discounts, (online) events and many more.
- Rewards Experience @ Intel Poland: https://jobs.intel.com/pl/benefits
- We offer a total compensation package that ranks among the best in the industry. Annual Salary Range for this job which could be performed in Poland is: 215 740,00 zł - 388 330,00 zł.
Minimum Qualifications
- Bachelor's degree in AI, Computer Science, Computer Engineering, Mathematics, Physics, or a related field.
- 4+ years of relevant experience with a Bachelor's degree, or 3+ years with a Master's degree.
- Advanced expertise in Python programming.
- Hands-on experience with AI inference and large language models (LLMs).
- Demonstrated proficiency in PyTorch.
- Solid foundation in AI frameworks, machine learning algorithms, and software engineering practices.
- Strong problem-solving skills with experience in debugging and designing optimized software and algorithms.
- Proficiency in Linux environments from a user perspective.
Preferred Qualifications
- Experience in performance profiling and optimization for AI workloads, including reading and interpreting hardware-level profiles.
- Familiarity with parallel and distributed computing concepts and collective communication libraries.
- Familiarity with vLLM or another LLM inference serving framework.
- Track record of accepted contributions to a major open-source AI project.
- Understanding of numerical precision and quantization formats (FP8, INT8, INT4) and their accuracy implications.
- Knowledge of writing/optimizing GPU compute kernels is a plus.
- Creativity and innovative thinking in solving technical and system-level challenges.
- Strong communication skills and ability to work across global teams.
