What the posting requires
- Required
- PyTorch
- Distributed training
- RL
- Systems
- SFT
- Shipped models
- Model improvement
- Scarce data
- PPO
- GRPO
- Preferred
- Inference engines
- Agentic RL
- Distillation
- vLLM
- Multi-turn RL
- Model training
These tags are our reading of the posting. They can miss something; the original posting is the reference.