Developer Technology Engineer - AI
On-siteShanghai, Shanghai, China or Beijing, Beijing, China
Job Summary
Work directly with key application developers to understand problems and build optimized core parallel algorithms for GPUs, focusing on training and inference for large language models. Contribute to frameworks like Megatron and TRTLLM while collaborating with architecture and research teams to influence next-generation platforms. Spearhead advancements in distributed training by refining communication libraries and designing efficient data transfer strategies for interconnect topologies. Engage in deep optimization of high-performance operators including GPU kernel tuning and compiler improvements to support customers and open-source projects.
Required Qualifications
- A degree or equivalent experience from a university in an engineering or computer science related field
- 2+ years of work experience
- Solid understanding of C, C++, Python, or Fortran
- Strong knowledge of software development, programming techniques, and algorithms
- Strong mathematical fundamentals, including linear algebra and numerical methods
- Background in parallel programming and accelerated computing, with comprehensive knowledge of parallel architectures and methods for performance analysis and tuning
- Solid software engineering fundamentals and system architecture thinking, with the ability to build modules and drive engineering practices in complex systems
- Strong communication and cooperation abilities, with the capability to work efficiently alongside architecture, research, and software product teams to promote optimization from concept to production
Desired Qualifications
- A masters or doctoral degree
- Experience in GPU programming
- Experience in full-stack performance analysis and optimization within at least one of these areas: large language models and high-performance computing
- Having expertise ranging from operator-level through framework-level to algorithm-level optimization
- Experience in distributed communication optimization
- Familiarity with remote direct memory access, GPU interconnects, collective communication algorithms, and associated open-source libraries used in large-scale model training and inference
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.