AI Infra Engineer(Agentic RL 训练框架)
深圳、北京、上海
全职
智能机器人板块
职位描述
参与机器人大模型强化学习训练框架的研发与优化,面向不同模型、训练方式和业务场景,完善训练与推理能力,提升框架的稳定性、扩展性和运行效率。通过框架开发、性能分析与算法工程协作,支撑大规模强化学习实验和业务训练,推动算法能力高效落地。 【职位描述】 1. 训练框架研发:负责强化学习训练框架的设计、开发与迭代,完善 GRPO、PPO、On-Policy Distillation 等训练方式的完整流程、数值正确性与运行稳定性,统一训练数据、优化目标与参数更新的扩展接口; 2. 核心模块与多后端适配:参与训练、推理、轨迹管理、奖励计算等核心模块研发,推进模块解耦与服务化,完善对 FSDP、Megatron、vLLM、SGLang 等训练与推理后端的适配层,支持不同模型、训练方式和业务场景的接入; 3. 评测与性能优化:建设核心训练场景的 benchmark、profiling 与 CI 回归体系,理解不同训练场景的运行特征,定位影响端到端效率与资源利用率的关键瓶颈,结合真实业务负载开展优化并推动成果落地; 4. 业务训练闭环:与算法团队协作完成具身模型 RL 后训练等真实业务的训练闭环,参与训练需求分析、技术方案设计与联调验证,支持新训练方法的接入与工程化落地; 5. 自动化与研发效能:完善任务配置、实验追溯、排障诊断与模型交付工具及文档,降低实验配置、管理与排障成本,提升框架使用体验与算法研发效率。
职位要求
投递

XPeng is a leading Chinese Smart EV company that designs, develops, manufactures, and markets Smart EVs that appeal to the large and growing base of technology-savvy middle-class consumers. Its mission is to drive Smart EV transformation with technology and data, shaping the mobility experience of the future. In order to optimize its customers’ mobility experience, XPeng develops in-house its full-stack advanced driver-assistance system technology and in-car intelligent operating system, as well as core vehicle systems including powertrain and the electrical/electronic architecture. XPeng is headquartered in Guangzhou, China. In 2021, the Company established its European headquarters in Amsterdam, along with other dedicated offices in Copenhagen, Munich, Oslo, and Stockholm.The Company’s Smart EVs are mainly manufactured at its plant in Zhaoqing and Guangzhou,Guangdong province.
For more information, please visit https://heyxpeng.com.