大疆大模型后训练专家
社招全职算法地点:深圳 | 上海 | 北京状态:招聘♡ 收藏
工作描述
岗位职责: 1、负责 DJI 飞行器、扫地机等业务场景下的基模后训练、任务适配和效果优化; 2、基于预训练模型,进行 SFT、指令微调、模仿学习、偏好优化、离线/在线强化学习、安全约束训练等; 3、面向具体产品任务提升模型效果,包括飞行避障、目标跟随、路径规划、智能构图、扫地机导航、覆盖清扫、语义避障、脱困等; 4、设计任务级数据集和训练样本,结合真实设备数据、用户反馈、失败案例进行持续迭代; 5、建立后训练评测体系,围绕任务完成率、安全性、稳定性、端侧延迟、功耗、用户体验等指标优化模型; 6、与飞控、导航、感知、系统、端侧部署团队协作,确保模型输出安全、稳…
登录查看完整工作描述
微信扫码,1秒登录
包括英文材料
SFT+
https://cameronrwolfe.substack.com/p/understanding-and-using-supervised
Understanding how SFT works from the idea to a working implementation...
强化学习+
https://cloud.google.com/discover/what-is-reinforcement-learning?hl=en
Reinforcement learning (RL) is a type of machine learning where an "agent" learns optimal behavior through interaction with its environment.
https://huggingface.co/learn/deep-rl-course/unit0/introduction
This course will teach you about Deep Reinforcement Learning from beginner to expert. It’s completely free and open-source!
https://www.kaggle.com/learn/intro-to-game-ai-and-reinforcement-learning
Build your own video game bots, using classic and cutting-edge algorithms.
RLHF+
[英文] What is RLHF?
https://aws.amazon.com/what-is/reinforcement-learning-from-human-feedback/
Reinforcement learning from human feedback (RLHF) is a machine learning (ML) technique that uses human feedback to optimize ML models to self-learn more efficiently.
https://www.ibm.com/think/topics/rlhf
Reinforcement learning from human feedback (RLHF) is a machine learning technique in which a “reward model” is trained with direct human feedback, then used to optimize the performance of an artificial intelligence agent through reinforcement learning.
还有更多 •••
相关职位
社招3年以上技术类-算法
1、有2~5年的大模型后训练经验,专业不限(计算机/软工/数学等相关背景更易上手) ; 2、大模型相关经验,包括但不限于模型微调、强化学习等; 3、对AI有朴素的热情,有AI信仰,愿意用AI重构业务场
更新于 2026-09-28杭州
社招1-3年J0011
1、在 NLP、LLM、深度学习、强化学习方面有一定研究基础,熟悉主流大模型和算法,并有丰富的实践经验; 2、较强的工程实现能力,熟练掌握 pytorch,熟悉DeepSpeed、Megatron等
更新于 2026-07-03北京
社招3年以上WXG公共技术
1.计算机科学、数学、人工智能等相关专业硕士及以上学历; 2.具备良好的数理基础和 NLP 技术基础,能够熟练使用 Megatron,HuggingFace,DeepSpeed,PyTorch 等框
更新于 2026-06-16北京