Gradiant is seeking an engineer to identify bottlenecks across the inference stack for open-weight models. You will measure targets on NVIDIA and AMD hardware, design kernels and memory layouts, and push changes to runtimes and serving paths.
The role emphasizes turning research into production services and sharing findings publicly. You should be proficient in Python and a systems language (C++ or Rust), with experience in GPU programming or low-level hardware considerations and a strong grasp
#J-18808-Ljbffr
Open-Weight Inference Systems Architect employer: Gradiant
Gradiant is an exceptional employer that fosters a collaborative and innovative work culture, perfect for those passionate about bridging the gap between research and practical application. Located in London, employees benefit from a vibrant tech community, ample opportunities for professional growth, and a commitment to meaningful work that impacts the engineering landscape. With a focus on employee development and a supportive environment, Gradiant stands out as a rewarding place to advance your career.
