LLM Post-Training Engineer Graduate (Research & Product) - 2027 Start
This position is no longer accepting applications(closed Aug 19, 2026).
Summary
Build and evaluate large language models by tuning instruction and preference data, implementing reward models, and ensuring safety and helpfulness in production systems.
- Analyze and process large scale datasets
- Build model evaluation pipelines
- Collaborate with engineering teams for production AI
- Evaluate model helpfulness and safety
- Optimize instruction tuning
- Optimize preference tuning
- Research and implement human preference learning
- Research and implement reward modeling
- Support post training strategy development
