Post-Training
Core
Advancing post-training research, including reward modeling and RL, to improve large-scale AI models.
Role type
Post-training research engineer
Builds
Data collection, evaluation, and post-training methods for conversational AI models
Domain
Artificial Intelligence / Machine Learning
Deliverable
production ML models
Required skills
reward modeling, RL, post-training techniques, large-scale AI development, conversational AI deployment, C/C++/C#/Java/JavaScript/Python
Preferred skills
passion for learning new technologies, staying updated on AI trends
Technologies
C, C++, C#, Java, JavaScript, Python
Responsibilities
Develop data collection, evaluation, and post-training methods; Design hypotheses and experiment plans for model performance iteration
Seniority
Mid-to-Senior, hands-on IC
Sourced via microsoft · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.