Research Engineer

Build and improve generalist audio models end-to-end across data, pre-training, post-training, and evaluation. Research multimodal architectures and efficient codecs, then post-train models for LLM-like instruction following and in-context learning over text and audio. Develop scalable pre-training/post-training workflows (e.g., SFT/RLHF-style, distillation, preference optimization) plus data and compute pipelines with evaluation harnesses. Work with a small team and high compute to ship research to production quickly.