Software Engineer, Reinforcement Learning
Core
Building frontier reinforcement learning systems, environments, and training pipelines to improve large language models and agentic capabilities for millions of users.
Role type
Senior IC software engineer (reinforcement learning)
Builds
RL environments, rollout systems, training pipelines, reward models, and evaluation benchmarks for large-scale generative models.
Domain
Artificial Intelligence / Large Language Models / Reinforcement Learning
Deliverable
production ML models
Required skills
Reinforcement learning, large language model post-training, distributed training, GPU inference, reward modeling, experiment design, system architecture, data curation, technical leadership
Preferred skills
Multi-team initiative leadership, cross-functional influence, mentorship, roadmap planning, observability engineering
Technologies
Python, C++, C#, Java, JavaScript, GPUs, open-source ML frameworks
Responsibilities
Set technical direction for RL initiatives; build and scale RL environments and training pipelines; develop reward models and training datasets; run experiments to improve model capabilities; partner with evaluation teams to define benchmarks; improve reliability and throughput of RL experiments; mentor engineers and shape technical culture.
Seniority
Senior, hands-on IC with leadership responsibilities