- Beijing, China
1–7 jobs· newest first


Senior
$151K–$231KOn-site · Full-time · Senior

$200K–$400K
Senior

On-site · Full-time · Principal

On-site · Full-time · Senior
+10K new in the last hour
Responsible for end‑side model deployment, optimization, and system integration across heterogeneous CPU/GPU/NPU environments, ensuring performance, latency, throughput, and stability balance.
Responsible for the full-link deployment of on-device models, including model conversion, quantization, compilation, runtime integration, operator adaptation, memory management, version compatibility, and phased release. Focus on performance profiling, bottleneck identification, and inference optimization for CPU/GPU/NPU heterogeneous computing environments (Windows/Linux/Android).
BLUE ORIGIN · Posted Nov 13, 2026
As an Application Software Engineer focused on Machine Learning (ML) Systems, you will be responsible for ensuring our customers' AI models run with maximum efficiency on our unique orbital platform. This is a deep, technical role for a software engineer who is passionate about the low-level details of AI model performance and is excited to work at the intersection of machine learning and aerospace.
VA applicants is $164,652.00 - $230,512.80 CO applicants is $150,931.00 - $211,303.05 WA applicants is $164,652.00 - $230,512.80 Other site ranges may differ

RadixArk · Posted Feb 17, 2026
Design and implement high-performance kernels for AI workloads, optimize compiler and runtime stacks, improve communication efficiency across large GPU clusters, and develop tooling for profiling and performance analysis.
Depending on background, skills, and experience, the expected annual salary range for this position is $200,000 - $400,000 USD + equity.
Lead software engineering efforts to develop and optimize AMD’s AI compilers and runtimes for Ryzen AI SoC, enhancing performance for vision, language, and generative AI workloads.
Drive technical direction and execution of AI and Generative AI workloads on GPU platforms.
Lead architectural definition and specification of next-generation ML compute IP and acceleration blocks for Google Cloud AI silicon.