Note: This README is generated with AI from my personal website: nanjiangwill.com.
AI researcher/engineer.
I want to:
- build AI that does not replicate the human cognition paradigm, but creates its own.
- build reliable and trustworthy systems for large-scale experiments.
- @Modal Labs: Training / Infra
- Previously @Amazon AGI SF Lab: RL post-training
- Working on large-scale RL systems and contributing to slime/miles
- Non-sequential decoding and reasoning
- Stable and scalable RL
- Better multi-modal representation




