Remote Model Training Research Scientist

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

Benefits offered by this job

Equity compensation

Remote-first workforce

Health insurance

Job summary

micro1 seeks a Member of Technical Staff, Model Training (post-training research) to push the boundaries of post-training methods for language and multimodal models. You will translate research insights into scalable training pipelines and contribute to high-impact experiments in a remote-first setup.

You will collaborate on approaches like SFT, RL, and distillation, and you will design rigorous experiments to quantify improvements in generalization and reasoning across tasks.

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.
• Experience implementing and evaluating post-training methods like SFT, RL, and distillation.

Responsibilities

• Research, implement, and scale advanced post-training methods across large language and multimodal models.
• Investigate learning objectives, optimization dynamics, and data strategies to improve training stability and efficiency.
• Design and run rigorous experiments, ablations, and evaluation frameworks to measure generalization and reasoning.

Skills

Machine learning

Deep learning

Experiment design

Python

PyTorch

Tools

PyTorch

TensorFlow

Job description

micro1 seeks a Member of Technical Staff, Model Training (post-training research) to push the boundaries of post-training methods for language and multimodal models. You will translate research insights into scalable training pipelines and contribute to high-impact experiments in a remote-first setup.

You will collaborate on approaches like SFT, RL, and distillation, and you will design rigorous experiments to quantify improvements in generalization and reasoning across tasks.