Hands-on experience building reasoning models via post-training techniques — supervised fine-tuning (SFT) on chain-of-thought/reasoning traces and reinforcement learning (RL) methods (e.g., RLHF, RLVR, PPO, GRPO, DPO) — including reward/verifier design and evaluating gains in multi-step reasoning. 7+ years of industry experience in software engineering, data science, or machine learning, including technical leadership experience.