{"id":2730398,"url":"https://alion.io/job/topilot-uandaoduansuanfagongchengshi","title":"端到端算法工程师","company":{"id":4442012,"name":"Utopilot","domain":"utopilot.com.cn","url":"https://alion.io/company/utopilot","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Feishu","truth_index":{"grade":"C","score":56,"open_postings":19,"ghost_share":0.737,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":null,"computed_at":"2026-10-17T05:46:00Z"}},"role":"AI/ML","role_family":"AI/ML","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":["Shanghai, 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":"C++","optional":false},{"name":"Imitation Learning","optional":false},{"name":"Reinforcement Learning","optional":false}],"status":"live","first_seen_at":"2026-01-13T09:23:21Z","employer_posted_date":"2026-10-16","last_verified_at":"2026-10-17T12:17:08Z","board_verified":true,"closed_at":null,"days_open":277,"trust":{"level":"ghost","repost_count":0,"flags":["stale","company_stale"],"days_open":276},"description":"岗位职责 / Responsibilities\n一、核心职责\n1. 端到端深度学习算法设计与创新\n研究、设计并实现应用于自动驾驶的端到端（End2End）深度学习算法架构，整合感知、预测与规划全链路功能。\n开发基于大规模真实驾驶数据的模型训练、微调与优化技术，攻克端到端链路中的数据分布偏移、场景泛化性差等核心问题。\n探索端到端算法在复杂驾驶场景中的应用，如：城市道路多路口交互、环岛绕行、避让突发障碍物、极端天气行驶等核心任务，提升算法对复杂场景的适应性。\n2. 算法开发与工程实现\n将前沿的端到端算法研究成果转化为可应用于L4级无人驾驶系统的工程化模块，搭建高效、稳定的算法研发与验证流程。\n开发数据处理、特征工程、模型训练、推理加速全链路工具链，优化数据加载、训练并行、推理部署等关键环节的性能。\n针对车载计算平台（如NVIDIA DRIVE Orin/Thor）进行算法优化，通过模型剪枝、量化、蒸馏、算子优化等技术，满足自动驾驶系统的实时性与低延迟要求。\n3. 评测体系构建与性能迭代\n设计并构建端到端算法的全维度评测体系，涵盖安全性、合规性、舒适性、效率等核心指标，制定离线仿真评测、封闭场地测试、公开道路验证的全流程评测方案。\n基于评测结果进行算法性能归因分析，定位感知偏差、预测不准、规划不合理等问题，驱动算法模型与参数的迭代优化。\n建立算法异常案例库，针对临界场景、失败案例进行专项优化，持续提升端到端系统的鲁棒性与可靠性。\n4. 系统集成与落地验证\n将端到端算法模块无缝集成到自动驾驶软件栈，协同感知、底盘控制、人机交互等模块团队，保障全系统的兼容性与协同性。\n在仿真平台、测试车队上开展端到端算法的大规模验证工作，收集真实场景下的运行数据，完成算法从研发到落地的全流程验证。\n参与L4级无人驾驶产品的算法落地推进工作，解决工程化落地过程中的技术瓶颈，确保算法满足量产级别的性能与安全要求。\n5. 前沿技术追踪与团队赋能\n持续跟踪端到端学习、模仿学习（Imitation Learning）、强化学习（Reinforcement Learning）、深度生成模型（Deep Generative Model）等领域的最新研究进展，以及自动驾驶行业的技术趋势。\n在团队内部分享前沿技术洞察、算法研发经验与项目实践成果，推动团队技术能力的整体提升，引领端到端算法方向的技术创新。\n任职要求 / Requirements\n1. 教育背景\n计算机科学、机器学习、人工智能、机器人学、电子工程等相关领域的硕士及以上学历。\n2. 技术能力\n深度学习基础扎实：精通深度学习核心理论，深入理解端到端学习、模仿学习、强化学习等关键技术原理。\n编程与工程能力：精通C/C++、Python编程语言，具备优秀的软件工程能力和良好的代码规范; 熟悉Linux开发环境，熟练使用Git等版本控制工具。\n算法与数据基础：具备扎实的数据结构与算法基础，能够独立设计并实现复杂的算法逻辑; 熟练处理大规模自动驾驶数据集，熟悉数据清洗、标注、增强等全流程工具与方法。\n框架与工具熟练：精通深度学习框架PyTorch，熟悉模型训练、调优、部署相关的工具链TensorRT等。\n3. 经验要求\n3年及以上自动驾驶领域端到端算法研发经验，具备完整的算法从设计、训练、优化到落地验证的全流程项目经验。\n具备End2End Planning、Deep Generative Model、Imitation Learning、Reinforcement Learning等至少一个方向的核心研发经历。\n有复杂系统工程经验，能够应对自动驾驶端到端算法落地过程中的多模块协同、性能优化等工程化挑战。\n4. 个人素质\n出色的分析和解决复杂技术问题的能力，能够在高压环境下快速定位并攻克算法与工程瓶颈。\n强烈的自驱力、创新意识和探索精神，对自动驾驶前沿技术充满热情，愿意投入技术研发与创新工作。\n优秀的沟通能力和团队协作精神，能够高效协同跨模块、跨团队成员推进项目落地。\n三、加分项\n1. 有L4级无人驾驶产品端到端算法应用落地经验，深刻理解自动驾驶行业的安全规范与合规要求。\n2. 在顶级会议（CVPR、ICCV、ECCV、NeurIPS、ICML、ICLR、CoRL、RSS、ICRA、IROS等）发表过端到端学习、自动驾驶相关论文。\n3. 有车载嵌入式平台（如NVIDIA DRIVE Orin/Thor）算法部署与优化经验，熟悉实时性优化、功耗控制等车载场景核心需求。","description_format":"text","description_chars":1871,"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":"2026-10-16T17:43:04Z"}],"visa":[],"liveness":{"score":2,"band":"cold","label":"Long shot","p_open":1,"p_active":0.084,"p_room":0.28,"age_days":276,"expected_fill_days":22,"reasons":["conf:4","stale_co","ghost","win:tail","crowd:"],"computed_at":"2026-10-17T05:46:00Z"},"pay":null,"html_url":"https://alion.io/job/topilot-uandaoduansuanfagongchengshi","json_url":"https://alion.io/job/topilot-uandaoduansuanfagongchengshi.json","meta":{"generated_at":"2026-10-17T14:28:34Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":19506,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-18T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":4442012},"rest":"https://alion.io/mcp/rest/get_company?id=4442012"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Ftopilot-uandaoduansuanfagongchengshi"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Ftopilot-uandaoduansuanfagongchengshi"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Ftopilot-uandaoduansuanfagongchengshi"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/topilot-uandaoduansuanfagongchengshi\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Ftopilot-uandaoduansuanfagongchengshi"}]}