Research Engineer (Reinforcement Learning)

LiveKit is seeking a Research Engineer specializing in Reinforcement Learning to build post-training systems for voice and text agents. You will own the synthetic data pipeline, run training experiments, and ship models into production.

• Build environments and verifiers for model training
• Own the synthetic data pipeline
• Run end-to-end training experiments
• Ship models into production and improve them
• Strong Python engineering skills
• Experience carrying a model from data to production