System Engineer (Token Factory)

Accountabilities

• Develop and optimize low-level kernels, runtime components, and system software responsible for high-performance AI inference workloads.


• Improve inference engine performance across GPU platforms by identifying bottlenecks and implementing advanced optimization techniques.


• Profile, debug, and resolve system-level and hardware-level performance issues across CPU and GPU environments.


• Integrate support for emerging GPU architectures and next-generation hardware platforms.


• Collaborate closely with machine learning and backend engineering teams to optimize end-to-end execution pipelines.


• Contribute to the continuous improvement of large-scale AI infrastructure through technical innovation, performance analysis, and system-level problem solving.

Requirements

• Strong proficiency in C++ development or deep expertise in GPU programming focused on low-level, high-performance computing and memory management.


• Experience with GPU programming or systems-level software development, including operating system internals, kernel modules, device drivers, or comparable areas.


• Hands-on experience using profiling and debugging tools to analyze CPU and GPU performance issues and optimize code based on findings.


• Strong understanding of CPU/GPU architecture, memory hierarchy, and hardware performance considerations.


• Familiarity with GPU computing technologies such as CUDA, ROCm, CUTLASS, Triton, Pallas, Mosaic GPU, or similar frameworks is highly valued.


• Experience with machine learning inference runtimes such as TensorRT, TVM, or comparable technologies is a plus.


• Knowledge of Linux internals, compiler toolchains, drivers, and performance analysis tools such as perf, VTune, Nsight, or ROCm profiler is beneficial.


• Familiarity with modern inference engines and AI deployment frameworks is considered an advantage.


• Strong problem-solving skills, technical curiosity, and ability to collaborate effectively in a fast-paced engineering environment.

Benefits

• Competitive compensation package.


• Fully remote working flexibility within Europe.


• Opportunity to work on impactful AI infrastructure projects at global scale.


• Strong opportunities for career development and continuous technical learning.


• High level of ownership and autonomy in a collaborative engineering culture.


• International environment with talented teams working on advanced AI technologies.


• Opportunity to contribute to the evolution of large-scale GPU computing and AI deployment platforms.

Deze vacature komt van ats_lever. Originele vacature bekijken ↗