{"id":1390701,"url":"https://alion.io/job/xiaopeng-embodied-ai-system-engineer","title":"Embodied AI System Engineer","company":{"id":1822489,"name":"XPeng","domain":"xiaopeng.com","url":"https://alion.io/company/xiaopeng-com","size_band":"1001-5000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Feishu","truth_index":{"grade":"B","score":76,"open_postings":958,"ghost_share":0.324,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":144,"computed_at":"2026-10-03T05:45:00Z"}},"role":"DevOps","role_family":"DevOps","seniority":null,"employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Shenzhen, China"],"countries":["CN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Apache TVM","optional":false},{"name":"C++","optional":false},{"name":"CUDA","optional":false},{"name":"CUDA Toolkit","optional":false},{"name":"Embodied AI","optional":false},{"name":"Linux","optional":false},{"name":"LLM","optional":false},{"name":"ONNX","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"PyTorch C++","optional":false},{"name":"TensorRT","optional":false},{"name":"Vision-Language-Action","optional":false},{"name":"VLM","optional":false}],"status":"live","first_seen_at":"2026-07-22T07:09:45Z","employer_posted_date":"2026-09-28","last_verified_at":"2026-10-04T00:46:32Z","board_verified":true,"closed_at":null,"days_open":73,"trust":{"level":"ok","repost_count":0,"flags":["company_stale"],"days_open":72},"description":"岗位职责 / Responsibilities\n1. 模型量化与压缩（核心）：面向具身大模型（VLA），主导 PTQ（训练后量化）与 QAT（量化感知训练）等量化方案的设计与落地，在低比特/混合精度下完成模型压缩，兼顾模型效果与运行效率。\n2. 精度与性能对齐：建立量化前后的精度评估与回归验证机制，解决量化带来的精度损失问题，保障压缩后模型在真实任务上的效果稳定、可交付。\n3. 推动模型高效落地：作为模型侧的核心推动者，与硬件、工程及测试团队紧密协作，输出量化模型与优化方案，驱动大模型与机器人感知、决策、控制模块的系统级集成与落地，打通模型能力落到真实本体的 last mile。\n4. 技术影响力：紧跟模型压缩、量化与推理优化领域的最新进展，通过技术攻坚与方案沉淀，持续提升模型在资源受限场景下的运行效率，形成技术影响力。\n任职要求 / Requirements\n1. 教育背景：计算机、电子工程、人工智能、自动化等相关专业本科及以上学历; \n2. 算法与工程基础：具有扎实的机器学习/深度学习基础，深入理解 VLM / LLM / VLA 等大模型的结构与推理过程; \n3. 编程与工具能力：精通 Python / C++，熟悉 Linux 环境与网络/性能分析; 熟练使用 PyTorch 等主流深度学习框架，具备优秀的系统级代码实现能力; \n4. 核心专业技能：精通模型量化技术，深入掌握 PTQ 与 QAT 的原理与工程实践，有大模型/多模态模型量化压缩并完成精度对齐的实战经验; 熟悉主流量化工具链与推理加速方案（如 TensorRT / ONNX / TVM / CUDA 等），了解算子优化与异构计算者优先; \n5. 综合素质：对具身智能（Embodied AI）及机器人系统有浓厚兴趣; 具备良好的跨团队沟通协作能力与复杂问题解决能力，能作为模型侧核心，在\"研究-工程-硬件\"多方之间高效推动项目落地。","description_format":"text","description_chars":813,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[{"language":"Chinese","level":"Advanced (C1)","optional":false}]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":[],"lifecycle":[{"event":"open","at":"2026-09-28T11:28:13Z"}],"visa":[],"liveness":{"score":57,"band":"ok","label":"Likely open","p_open":1,"p_active":0.79,"p_room":0.72,"age_days":72,"expected_fill_days":144,"reasons":["conf:2","velocity","win:mid","crowd:brand"],"computed_at":"2026-10-03T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/xiaopeng-embodied-ai-system-engineer","json_url":"https://alion.io/job/xiaopeng-embodied-ai-system-engineer.json","meta":{"generated_at":"2026-10-04T00:56:52Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","usage":{"tier":"crawler","counted_by":"address","units_charged":1,"used_today":1226,"day_limit":5000,"remaining_today":3774,"minute_limit":60,"resets_at":"2026-10-05T00:00:00Z"}}}