Inception Labs
Member of Technical Staff, RL Infra
San Mateo, United States · On-site · Staff · Full-time · Posted Mar 10, 2026
- Education
- BS/MS/PhD in Computer Science, Engineering, or a related field (or equivalent experience).
About the job
Designs and operates scalable, reliable infrastructure for reinforcement learning and post-training workloads for large AI models.
What you'll do
- Build and optimize infrastructure for large-scale reinforcement learning and post-training workloads.
- Improve reliability, scalability, and throughput of RL pipelines and distributed workloads.
- Develop monitoring and observability tools for uptime, debugging, and reproducibility.
What they ask for
- Understanding of ML frameworks from a systems perspective, including PyTorch, TensorFlow, Ray, or Megatron.
- Experience with reinforcement learning workloads such as PPO, DPO, RLHF, or reward modeling.
- Experience with Docker, Kubernetes, and CI/CD pipelines.
Nice to have
- Experience building and maintaining language models with tens of billions of parameters or more.
- Experience with Kubeflow or Airflow; performance optimization and profiling of ML systems.
Tools
PyTorch, TensorFlow, Ray, Megatron, PPO, DPO, Docker, Kubernetes
AI focus
Builds infrastructure for reinforcement learning and post-training of large AI models, including RL training pipelines and reward workflows.
Model-written summary · the original posting is authoritative