Find jobs in AI/ML, Data Science and Big Data
2 results
for FP8 Quantization
(Skill/Tech stack)
-
具身世界模型推理INFRA工程师 - XiaomiRobotics CNY 240K-480KCFG Parallelism | Diffusion Models | Expert parallelism | FP8 Quantization | Multi Token PredictionSenior-level Full Time北京13d ago
-
Performance Engineer, GPU USD 280K-850KBandwidth Optimization | CUDA | Cluster Orchestration | Collective communication | Custom OperatorsFlexible working hours | Generous vacation | Hybrid work 25 percent | Optional equity donation matching | Parental leaveSenior-level Full TimeSan Francisco, CA | New York …1mo ago