{"code":0,"data":{"job_post_detail":{"id":"7498320213524742252","title":"Miclaw-移动端 AI 性能专家 (Engine \u0026 Efficiency)","description":"1. 引擎调优：负责 Android/iOS、与云端 Mimo 或本地 ExecuTorch/ncnn 的底层接入与硬件加速（NPU/GPU/Metal）。\n2. 效率突破：实现 Speculative Decoding (投机采样) 或 Prompt Caching，在手机端将 TTFT（首包延迟）降至极致。\n3. 性能监控：建立全链路监控指标体系，关注 Tokens/sec、ITL (Token 间延迟) 以及 Agent 后台运行时的功耗曲线。\n4. 资源调度：解决多 Agent 并发请求时的资源竞争问题，防止手机卡顿或发热降频。","requirement":"1. 深厚的移动端开发功底（C++/Rust 为佳，Obj-C/Swift/Kotlin 为主）。\n2. 精通端侧模型量化技术（GGUF、EXL2、AWQ 等），能平衡模型精度与推理速度。\n3. 理解 Transformer 底层算子逻辑，有对 KV Cache 进行内存压缩或分页管理的实战经验。\n4. 硬核要求：能够从 Profiler 工具中定位瓶颈，并在极端网络/硬件环境下保持 Agent 请求的高稳定性。","recruit_type":{"id":"101","name":"全职","en_name":"Full-time","i18n_name":"全职","depth":2,"parent":{"id":"1","name":"社招","en_name":"Experienced","i18n_name":"社招","depth":1,"children":[],"active_status":1,"selectability":1},"children":[],"active_status":1,"selectability":1},"publish_time":1745839509261,"channel_online_status":1,"code":"A240371","job_id":"7498320213524676716","city_list":[{"code":"CT_11","name":"北京","en_name":"Beijing","location_type":3,"i18n_name":"北京","py_name":"beijing","mdm_code":"MDCY00000001","node_status":1}],"job_post_info":{"recruitment_type":{"id":"101","name":"全职","en_name":"Full-time","i18n_name":"全职","depth":2,"parent":{"id":"1","name":"社招","en_name":"Experienced","i18n_name":"社招","depth":1,"children":[],"active_status":1,"selectability":1},"children":[],"active_status":1,"selectability":1},"HighlightList":[],"JobChannelPublishList":[],"job_post_object_value_map":{},"address_list":[],"city_list":[],"correlation_job_list":[],"tag_list":[],"storefront_list":[],"target_major_list":[],"job_post_process_time_list":[],"job_level_id_list":[]},"city_info_list_for_delivery":[{"code":"CT_11","name":"北京","en_name":"Beijing","location_type":3,"i18n_name":"北京","py_name":"beijing","mdm_code":"MDCY00000001","node_status":1}],"tag_list":[],"storefront_mode":1,"storefront_list":[],"process_type":1},"recommend_job_post_List":[]},"message":"ok","error":null}