Member of Technical Staff — RL Research

About the Company

Nuance Labs is building photorealistic, real-time AI avatars with emotional intelligence: a full-duplex audiovisual system that can listen, speak, react, interrupt, and respond like a real person.

Responsibilities

• Build Nuance’s RL/post-training stack from 0→1 including rollout generation, policy optimization, and reward modeling
• Develop and scale post-training methods such as PPO, GRPO, DPO, and RLHF/RLAIF
• Design system abstractions for trainers, rollout workers, and data queues
• Build evaluation and feedback loops for omni behavior like turn-taking and emotional response
• Optimize end-to-end post-training loops for throughput, latency, and GPU utilization

Requirements

• Significant experience with RL, RLHF, RLAIF, post-training, or large-scale fine-tuning
• Deep understanding of policy optimization, reward modeling, and preference optimization
• Track record reasoning about model behavior like reward hacking and distribution shift
• Experience building RL/post-training pipelines with frameworks like verl, ms-swift, or OpenRLHF
• Experience with large-scale training or inference systems and GPU utilization
• Understanding of omni post-training for real-time audio-video-language interaction
• Strong software engineering fundamentals

Preferred Qualifications

• Prior 0→1 experience building post-training or agent training systems
• Experience with multimodal post-training for audio-video-language models
• Experience scaling mixed training/inference workloads across large GPU clusters
• Publications or substantial open-source contributions in RL or ML systems

Benefits

• HSA plan with ~$2,000 annual company contribution
• 15 days of PTO plus public holidays and a full week off at year-end
• Daily lunch, drinks, and snacks
• Commuter benefits
• Visa sponsorship available from day one