Research Engineer, Production Model Post-Training
Core
Train base models through the complete post-training stack to deliver production Claude models, implementing and scaling alignment methodologies like Constitutional AI and RLHF.
Role type
Senior IC research engineer (production model post-training)
Builds
Production-ready LLMs (Claude) via post-training pipelines
Domain
Generative AI / Large Language Models
Deliverable
production ML models
Required skills
Python, deep learning frameworks, distributed computing, training/fine-tuning LLMs, debugging complex training pipelines, scaling ML systems
Preferred skills
LLMs experience, AI safety and responsible deployment
Technologies
Constitutional AI, RLHF
Responsibilities
Implement and optimize post-training techniques at scale on frontier models; Conduct research to develop and optimize post-training recipes; Design, build, and run robust pipelines for model fine-tuning and evaluation; Develop tools to measure and improve model performance; Collaborate with research teams to translate emerging techniques into production; Debug complex issues in training pipelines and model behavior; Establish best practices for reliable, reproducible model post-training
Seniority
Senior, hands-on IC
