M
ML Engineer, Post-Training
LLMsRLHFPyTorchDistributed SystemsPython
About the role
Build and scale post-training infrastructure for large multimodal language models.
Responsibilities
Implement RLHF, SFT, and evaluation pipelines; optimize throughput and reliability.
Requirements
Experience training or fine-tuning LLMs; Python, PyTorch, distributed systems.
Benefits
Remote-first, top compensation, equity, flexible schedule, cutting-edge hardware.
Disclaimer: MMagic.ai connects talented people with AI companies around the world. While we work hard to feature quality opportunities, we don't independently verify employers, candidates, salaries, or hiring outcomes. We encourage you to research each opportunity and company before applying or making an offer.