Free Lesson
From Base Model to Agent: Inside NVIDIA’s PostTraining Stack
60 min
Aug 20, 2026 12:00 PM
Virtual (Zoom)
In this video
What you'll learn
Understand the Modern Post-Training Stack
See how SFT, RLVR and RLHF shape a base model into a capable assistant, reasoner and agent.
Design Rewards Models Can’t Game
Learn why strong verifiers are critical for RL, evals and reliable model improvement.
Choose the Right Model and Reasoning Budget
Learn when to use smaller vs. larger models and how reasoning depth impacts cost, latency and quality.
Think Like a Post-Training Systems Engineer
Understand how environments, rollout infrastructure and resiliency shape frontier model performance.
Why this topic matters
Modern AI capability is increasingly shaped after pre-training. This session breaks down the systems behind NVIDIA Nemotron, from SFT and RLVR to verifiers, reasoning control and infrastructure, so builders can understand how today’s reasoning and agentic models are actually trained, evaluated and improved.
