Member of Technical Staff, Model Training (post-training research) at micro1

Member of Technical Staff, Model Training (post-training research) at micro1micro1

Pay: USD 200,000–320,000 per yearly

Workplace: Remote

Skills: PythonJob Title: Member of Technical Staff, Model Training (post-training research)Job Type: Full-timeLocation: RemoteThe RoleIn this role, you will investigate how learning algorithms, training data, and evaluation methodologies interact to produce stronger reasoning, generalization, and agent capabilities. You will explore new approaches to reinforcement learning, distillation, and data-efficient training, translating research insights into scalable methods that improve model intelligence.This is a highly experimental role at the intersection of fundamental machine learning research and large-scale model development. You will have the opportunity to formulate research hypotheses, design ambitious experiments, and develop training methods that directly influence the capabilities of our models.What You'll Do1. Research, implement, and scale advanced post-training methods, including supervised fine-tuning (SFT), reinforcement learning (RL), and on-policy distillation (OPD), across large language and multimodal models. 2. Investigate learning objectives, optimization dynamics, exploration strategies, and credit assignment mechanisms to improve training stability, sample efficiency, and capability acquisition. 3. Develop and refine training recipes by jointly optimizing data mixtures, sampling strategies, curricula, and evaluation methodologies. 4. Design methods for learning from expert demonstrations, human preferences, corrections, and model-generated trajectories, identifying where human feedback delivers the greatest improvements. 5. Research the co-evolution of generators, reward models, and graders, developing approaches that improve both model performance and the quality of the training signals they consume. 6. Design rigorous experiments, ablation studies, and evaluation frameworks to measure generalization, reasoning, and performance on realistic downstream tasks. 7. Own research initiatives end-to-end, from identifying promis …truncated… lity, scientific rigor, an…Sign in to see the original postingBrowse more developer jobs on RoleBurst