← Back to Engineering Jobs

Inference & System Optimization Engineer

奇瑞全球創新(香港)有限公司 · Hong Kong

Apply

Job Description

Responsibilities: • End-to-end engineering from model to inference system, hardware platform, and edge-side deployment • Continuous optimization of inference cost, latency, throughput, and stability • Key technologies: quantization, pruning, distillation, KV Cache, Continuous Batching, Paged Attention, Speculative Decoding, CUDA/Ascend/PPU operator optimization, multi-GPU distributed inference, model compilation, and cloud-edge collaboration Requirements : • Experience in large model inference efficiency optimization

奇瑞
奇瑞全球創新(香港)有限公司 logo

奇瑞全球創新(香港)有限公司

Hong Kong

View other roles at 奇瑞全球創新(香港)有限公司

1 role at 奇瑞全球創新(香港)有限公司 on ExpatJobBoard

Similar Jobs

+595 English-speaking jobs in Hong Kong

New listings added daily · No Mandarin or Cantonese required

Join now to find your dream job in Hong Kong

  • English-only roles, guaranteed

    Every listing is checked with AI so you only see jobs that require English. No Cantonese. No Mandarin. No hidden language requirements.

  • Get ahead of the competition

    New roles are added daily so you can be one of the first applicants for the best chances of landing the job.

  • No junk listings

    We filter out volunteering roles, scam listings, and anything else that wastes your time.

  • Find jobs others miss

    We source many roles directly from company career pages, giving you access to opportunities most job seekers never see.