About this role
The role involves leading and executing the full post-training pipeline for large language models, including supervised fine-tuning, preference optimization, and reinforcement learning methods. Responsibilities also include designing advanced training paradigms, developing domain-specific data strategies, building reward models, and optimizing inference deployment.
Candidates must possess a Bachelor's degree in a relevant field and at least 8 years of industry experience, with strong hands-on expertise across the large model post-training pipeline. Essential qualifications include deep familiarity with preference learning and alignment techniques like DPO/GRPO, experience training specialized small models, and proven ability to deploy models using low-latency frameworks.
What they're looking for
Large Language ModelsPost-trainingAlignmentSupervised Fine-TuningPreference OptimizationReinforcement LearningDPOGRPO
Frequently asked questions
What does a Staff AI Engineer, Model Post-Training and Alignment at OKX do?
The role involves leading and executing the full post-training pipeline for large language models, including supervised fine-tuning, preference optimization, and reinforcement learning methods. Responsibilities also include designing advanced training paradigms, developing domain-specific data strat…
What skills does this Staff AI Engineer, Model Post-Training and Alignment role need?
Key skills for this role include Large Language Models, Post-training, Alignment, Supervised Fine-Tuning, Preference Optimization, Reinforcement Learning.
How much does a Staff AI Engineer, Model Post-Training and Alignment at OKX pay?
The employer did not list a salary for this role. Most similar Singapore roles publish their band on the job page.
Is this Staff AI Engineer, Model Post-Training and Alignment role remote, hybrid, or on-site?
This role is on-site, based in Hong Kong Island.
How do I apply for this Staff AI Engineer, Model Post-Training and Alignment role?
You can apply directly on OKX's careers page. ApplyLah can tailor your résumé and cover letter to this exact role in seconds first.