Member of Technical Staff — RL Research (New PhD Grad)

Own RL and post-training for large-scale omni models. Build Nuance’s RL/post-training stack from 0→1, including rollout generation, policy optimization, reward/reference model serving, data feedback loops, evaluation, checkpointing, observability, and debugging. Develop and scale post-training methods such as PPO, GRPO, DPO, rejection sampling, RLHF/RLAIF, online RL, and model-based data improvement. Design system abstractions connecting research ideas to production-scale RL runs (trainers, rollout workers, reward models, evaluators, data queues, experience buffers). Build evaluation and feedback loops for omni behavior (turn-taking, interruption, timing, emotional response, audiovisual coherence, real-time interaction quality). Optimize end-to-end post-training loop for throughput, latency, GPU utilization, and researcher iteration speed. Evolve the platform as algorithms and data sources change. Location: In-person in Seattle, five days a week; visa sponsorship available from day one.