GPU software engineer
About The Position
Come join our Communication Runtimes team as a Senior Software Development Engineer to develop cutting-edge software features and optimizations for Intel's communication libraries including libfabric, oneCCL (Collective Communication Library), ISHMEM (Shared Memory Access), and Intel MPI (Message Passing Interface). The team is looking for a strong developer to contribute to communication library development and performance engineering. We value diverse perspectives and believe that different backgrounds and experiences strengthen our technical solutions. We're committed to fostering an inclusive environment where all team members can contribute their best work. If you're passionate about how data flows in HPC/AI systems, and meet most of our qualifications, we'd love to hear from you. What we offer: • Inclusive team culture with employee resource groups. • Opportunities to expand expertise across different communication libraries. • Opportunity to build expertise with latest Intel GPUs and CPUs used in data centers. • Mentorship opportunities both as a mentor and mentee. • Career growth support and clear advancement paths. • Competitive compensation and comprehensive benefits. • Collaborative environment which contributes directly to the improvement of the upstream projects.
Requirements
- Bachelor’s degree in computer science, Electrical Engineering/ Electronics Engineering, Computer Engineering, Math, or in a STEM related field of study with 3+ years of experience
- 3+ years of experience with: Strong C and C++ programming/development and debugging skills.
- Development in Linux environments.
Nice To Haves
- Ph.D degree in Computer Science, Computer Engineering, or related field
- Experience developing performance optimizations that improve communications latency or throughput.
- Experience debugging problems at different layers of the hardware and software stack.
- Demonstrated upstream contributions and experience developing in an open-source environment.
- Track record of delivering complex technical projects independently.
- Experience collaborating with a diverse, distributed team.
- Experience with at least one or more of the following: Distributed computing. HPC communications libraries. Collective communication libraries. Developing software for GPUs.
- Developing software for one or more layers of the network communications stack: RDMA, RoCE, TCP/IP.
- Experience with GPU programming and parallel computing
- Experience with multithreaded programming.
- Experience with networking software stack.
- Handson experience with RDMA networking (InfiniBand and/or RoCE) and userspace RDMA APIs.
- Performance engineering with running benchmarks and workload analysis.
Benefits
- Inclusive team culture with employee resource groups.
- Opportunities to expand expertise across different communication libraries.
- Opportunity to build expertise with latest Intel GPUs and CPUs used in data centers.
- Mentorship opportunities both as a mentor and mentee.
- Career growth support and clear advancement paths.
- Competitive compensation and comprehensive benefits.
- Collaborative environment which contributes directly to the improvement of the upstream projects.
- Competitive pay
- Stock bonuses
- Health
- Retirement
- Vacation
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Mid Level
Number of Employees
5,001-10,000 employees
