Multimodal Reinforcement Learning Algorithm Researcher
Tasks
- Address reward hacking issues
- Conduct research on reinforcement learning algorithms for multimodal models
- Design reinforcement learning training frameworks
- Develop reward modeling strategies
- Explore next-generation reinforcement learning paradigms
- Improve training stability
- Train large scale multimodal models
Perks/Benefits
- N/A
Skills/Tech-stack
Autoregressive models | CPU acceleration | Deep learning | Diffusion Models | Distributed Training | GPU Acceleration | Inference Optimization | Model Inference | Model Inference Optimization | Model Training | Multimodal Learning | Reinforcement Learning | Reward Modeling
Education
Bachelor of Engineering | Bachelor of Science | Master of Science | PhD
Related jobs
-
Applied AI Researcher (OCR) SGD 106K-120KA/B | A/B Testing | B testing | CI/CD | Computer VisionCommuter benefits | Dental insurance | Employee assistance program | Flexible spending account | Health insuranceSenior-level Full TimeSingapore1d ago
-
Game ML Researcher Intern SGD 36K-36KC++ | Deep learning | Language Models | Large Language Models | Machine LearningEntry-level Internship Part TimeSingapore-CapitaSky16d ago
-
Game ML Researcher Intern SGD 36K-36KC++ | Deep learning | LLM | Language Models | Large Language ModelsEntry-level Internship Part TimeSingapore-CapitaSky16d ago
-
Quantitative Execution Strategist SGD 150K-225KC++ | Data Structures | Data Structures and Algorithms | Deep learning | Machine LearningNone Full TimeSingapore25d ago
-
Capacity | Cost modeling | Cross Sectional Prediction | Cross-validation | Data CurationSenior-level Full TimeEISG | Singapore – Marina One30d ago