Principal Research Engineer Post-Training

Skills

About the Role

You will define and drive the roadmap for mid- and post-training systems, balancing research innovation with reliable, scalable production systems. You will lead alignment and optimization research, develop evaluation frameworks, architect training and inference systems, improve data pipelines and model observability, and mentor researchers and engineers.

Requirements

• PhD in Computer Science, Machine Learning, AI, or a related field, or equivalent industry experience
• Significant experience leading technical projects or teams in machine learning, AI research, or large-scale distributed systems
• Deep understanding of transformers, reinforcement learning, alignment methods, and large language models
• Track record of delivering impactful research or applied ML systems in production environments
• Expertise designing, building, and maintaining production-quality ML systems and infrastructure
• Experience training, serving, debugging, and optimizing large-scale models on GPU-based systems
• Experience leading teams working on large language model training, mid-training, or post-training
• Experience with product experimentation, online evaluation, and A/B testing frameworks
• Strong software engineering skills
• Excellent communication skills and ability to lead cross-functional initiatives

Responsibilities

• Define and drive the technical roadmap for mid- and post-training systems
• Mentor researchers and engineers through technical guidance, design reviews, and career development
• Develop alignment algorithms, optimization techniques, and training objectives
• Advance reinforcement learning, preference optimization, supervised fine-tuning, and alignment methods
• Develop evaluation frameworks and quality signals for model performance
• Design efficient training and inference systems for large-scale generative models
• Architect scalable data pipelines for training datasets
• Optimize distributed training, GPU utilization, serving efficiency, experimentation platforms, data quality systems, and model observability

Benefits

• Health coverage for employees and their families with most premiums covered
• 401(k) contribution
• Paid parental leave of up to 20 weeks
• Four weeks of PTO
• Daily in-office catering
• Monthly DoorDash stipend
• Monthly wellness stipend