大模型Post-Training 算法工程师
上海
Mid-level Full Time
Tasks
- Analyze instruction following and general question answering bottlenecks
- Apply RLHF and RLAIF methods
- Apply SFT for model fine tuning
- Build automated high quality training data pipelines
- Design and implement model post training pipelines
- Implement iterative online data flywheel loop
- Optimize algorithms to improve model quality and stability
- Synthesize training data from human feedback and model feedback
Perks/Benefits
- N/A
Skills/Tech-stack
DPO | Data Engineering | Deep learning | MOE | Machine Learning | Mixture of Experts | PPO | PyTorch | Python | RLAIF | RLHF | Reinforcement Learning | SFT | Transformer
Education
Language: zh
Views:
10
Clicks:
4
Saves: 0
Related jobs
-
Entry-level Internship深圳17h ago
-
Entry-level Full Time上海18h ago
-
Entry-level Full Time上海18h ago
-
AI Feedback | Deep learning | Direct Preference Optimization | Fine Tuning | Human FeedbackMid-level Full Time上海20h ago
-
Senior-level Full Time上海、武汉、北京20h ago
-
算法工程师-大模型数据方向 CNY 240K-360KApache Spark | Clustering | Data Augmentation | Data Deduplication | Data GovernanceSenior-level Full Time上海20h ago
-
数据开发工程师（Ai知识方向） CNY 180K-300KContent processing | Data Governance | ETL | Elasticsearch | Information ArchitectureFull-time employmentMid-level Full Time上海20h ago
-
Mid-level Full Time上海20h ago
-
Senior-level Full Time上海20h ago
-
Senior-level Full Time上海20h ago
-
大模型算法工程师（开放域对话） CNY 180K-300KA/B | A/B Testing | Agentic reinforcement learning | B testing | DeepSpeedMid-level Internship上海、北京20h ago
-
Mid-level Full Time上海21h ago
-
大语言模型后训练/Agentic算法工程师 CNY 180K-360KDistributed Training | Function Calling | GRPO | Human Feedback | JSONEntry-level Full Time上海、北京21h ago
-
Senior-level Full Time上海21h ago
-
Embedded Software Eng. CNY 180K-300KARM | ASPICE | Automotive Software | Automotive Software Development | C#Mid-level Full TimeWuhu, CN1d ago
-
AI/LLM Application Engineer CNY 280K-330KAPI | Access Control | Audit Logging | Authentication | AuthorizationMid-level Full TimeShenyang - PIC, China1d ago
-
AI/LLM Application Engineer CNY 280K-330KAccess Control | Audit Logging | Backend Development | Citation Generation | Document chunkingMid-level Full TimeShenyang - PIC, China1d ago
-
AI/LLM Application Architect CNY 360K-600KAI architecture | API Integration | AWS Bedrock | Application development | Audit LoggingSenior-level Full TimeShenyang - PIC, China1d ago
-
Senior-level Full TimeLOC3254: No.3239 Shenjiang Road, Shanghai, Pudong …1d ago
-
Simulation Engineer, Industrial Physics and Robotics CNY 360K-600KCUDA | Co-simulation | Contact mechanics | Controller co simulation | Deformable BodiesComprehensive benefits package | Mentorship | Supportive work environmentSenior-level Full TimeChina, Shanghai1d ago
-
Sr. System Software Engineer CNY 240K-480KAAC | ARM | Audio/Video | Audio/Video Encoding | BashOn-site support | Remote support | Technical consulting | TrainingSenior-level Full TimeChina Shanghai1d ago
-
Senior Software Engineer - Robot Compute Platform CNY 240K-480KC# | C++ | CAN bus | CUDA | Deterministic systemsSenior-level Full TimeShanghai, China2d ago
-
Motion Control Engineer - Actuator Control Algorithms CNY 360K-600KAnti Windup | BLDC | Cogging Compensation | Commutation | Control loopSenior-level Full TimeShanghai, China2d ago
-
Robotics Lead/ System Architect CNY 360K-600KActuation | CAD | Computer Architecture | Embedded Systems | Humanoid roboticsSenior-level Full TimeShanghai, China2d ago
-
Embodied AI Intern CNY 45K-50KC++ | Computer Vision | Deep learning | Gazebo | Isaac SimHands on industry scale data annotation experience | Onsite work three days per week | Structured mentoringEntry-level Internship Part TimeShanghai, China2d ago