Research Engineer (Reinforcement Learning)

About this role

LiveKit is seeking a skilled Research Engineer to focus on post-training reinforcement learning for their voice and text agent platform. You'll be responsible for building environments, managing data pipelines, and deploying models to production, ensuring their effectiveness and reliability across various use cases. This role offers a chance to significantly impact a rapidly growing developer platform.

What you'll do

• Build and maintain model training environments and verifiers.
• Manage the synthetic data pipeline, including generation and quality control.
• Design and execute training experiments.
• Develop model evaluation frameworks.
• Adapt open-weight base models for specific tasks.
• Ship models to production and iterate based on real-world usage.

What they're looking for

• Python
• Reinforcement Learning
• Model Training
• Data Pipelines
• GPU Computing
• Fine-tuning
• Evaluation

Benefits

• Competitive salary and equity
• Health, dental, and vision benefits
• Flexible vacation policy
• Opportunity to shape a growing platform
• Collaboration with a senior team