Research Engineer - Environments, Data and Post-Training
Core
Develop novel post-training methods, training recipes, and evaluation systems to improve frontier AI model reasoning, tool use, and agentic behavior.
Role type
Senior IC research engineer (post-training & RL)
Builds
Scalable post-training pipelines, RLVR systems, data generation/filtering infrastructure, and evaluation benchmarks
Domain
Artificial Intelligence, Reinforcement Learning, Frontier Model Optimization
Deliverable
production ML models
Required skills
Post-training methods, Reinforcement Learning, Language-model evaluation, Data-centric ML, Experimental design, Python programming, Distributed systems
Preferred skills
Synthetic-data generation, Large-scale evaluation infrastructure, Cloud infrastructure, Open-source contributions
Responsibilities
Implement novel post-training methods for model reasoning and tool use, Design and run experiments on datasets and reward functions, Build RLVR and post-training pipelines at scale, Develop rubrics, evaluators, and benchmarks for training decisions, Create methods for measuring data quality and causal impact, Translate research questions into rigorous experiments and production systems
Seniority
Senior, hands-on IC
