Remote Model Training Research Scientist (Post-Training RL)

micro1; United States; Remote; USD 200,000 - 320,000; Full time

Benefits offered by this job

Equity compensation

Performance-based bonuses

Health insurance

401(k) plan

Job summary

micro1 in the United States is seeking a Member of Technical Staff, Model Training (post-training research) for a remote-friendly, full-time role. You will investigate how learning algorithms, training data, and evaluation methodologies interact to improve reasoning, generalization, and agent capabilities.

You will design and run large-scale experiments on reinforcement learning, distillation, and data-efficient training, translating research insights into scalable methods that influence our

Qualifications

• Strong foundations in machine learning, deep learning, optimization, and modern model training techniques.
• Hands-on experience training, fine-tuning, or post-training large-scale language or multimodal models.
• Deep technical expertise in reinforcement learning, model distillation, reward modeling, data selection, or learning dynamics.
• Strong proficiency in Python and PyTorch, with the ability to implement, debug, and optimize complex training pipelines.
• Experience designing controlled experiments, interpreting model behavior, and translating empirical findings into actionable research directions.
• Ability to independently navigate ambiguous research problems, formulate hypotheses, and iterate quickly based on experimental evidence.
• Strong analytical thinking and a research-driven mindset, with an emphasis on reproducibility and scientific rigor.

Responsibilities

• Research, implement, and scale advanced post-training methods across large models.
• Investigate objectives, optimization dynamics, exploration strategies, and credit assignment for training stability.
• Develop and refine training recipes by optimizing data mixtures, sampling strategies, curricula, and evaluation methods.
• Design methods for learning from expert demonstrations, human preferences, corrections, and model-generated trajectories.
• Research co-evolution of generators, reward models, and graders to improve performance and signal quality.
• Design rigorous experiments, ablations, and evaluation frameworks to measure generalization and reasoning.
• Own research initiatives end-to-end from direction to large-scale experiments and validation.

Skills

Machine Learning

Deep Learning

Optimization

PyTorch

Python

Reinforcement Learning

Job description

micro1 in the United States is seeking a Member of Technical Staff, Model Training (post-training research) for a remote-friendly, full-time role. You will investigate how learning algorithms, training data, and evaluation methodologies interact to improve reasoning, generalization, and agent capabilities.

You will design and run large-scale experiments on reinforcement learning, distillation, and data-efficient training, translating research insights into scalable methods that influence our