Ai 院--多模态团队--多模态理解算法研究员-强化学习方向
Tasks
- Align multi modal large models
- Apply human preference learning
- Build data collection cleaning pipeline
- Optimize VLM SFT RL training
- Process RL training data
Perks/Benefits
- N/A
Skills/Tech-stack
DPO | Data Processing | Data pipeline | DeepSpeed | Distributed Training | Linux | Megatron-LM | Multi-Modal | Multi-modal data | Multi-modal data processing | PyTorch | Python | RLHF | Reinforcement Learning | Transformer
Education
Roles
Related jobs
-
AVP, AI Solution Lead CNY 144K-240KArtificial Intelligence | Cloud Native | DataOps | DevOps | FlutterContinuous professional development | Flexible workingSenior-level Full TimeGuangzhou, Guangdong, China R5d ago
-
Mid-level Full Time北京 R7d ago
-
Entry-level Full Time北京 R7d ago
-
Mid-level Full Time北京 R8d ago
-
Mid-level Full Time北京 R8d ago
-
Diffusion Models | Flow matching | GPU Computing | Human Feedback | Multimodal LearningFully remote option | On-site flexibility | Open source collaborationMid-level Full TimeShanghai R12d ago
-
Consultant Specialist (GenAI Agent Platform) CNY 300K-420KAWS | Access Management | Audit Logging | Azure | CachingEntry-level Full TimeGuangzhou, Guangdong, China R16d ago
-
Entry-level Full Time上海、深圳 R21d ago
-
AI Engineer USD 100K-200KAPIs | Agentic Frameworks | Artificial Intelligence | Backtesting | Data integrationCollaborative work environment | Equity options | Innovation-driven cultureMid-level Full TimeShanghai, Shanghai, China R28d ago
-
AI platforms | API Development | Artificial Intelligence | Cloud AI | Cloud AI PlatformsMid-level Full TimeRemote, China R1mo ago