Research Engineer building and deploying production voice and multimodal ML models. Requires expert PyTorch, large-scale model training experience, and shipping user-facing ML systems.
Optimizes and extends ML model serving infrastructure for LLMs, speech, and vision models, focusing on high-throughput, low-latency inference using frameworks like VLLM and SGLang. Requires deep PyTorch expertise, systems programming, and performance engineering for reliable production deployment.
Research Engineer building and deploying production voice and multimodal ML models. Requires expert PyTorch, large-scale model training experience, and shipping user-facing ML systems.
Optimizes and extends ML model serving infrastructure for LLMs, speech, and vision models, focusing on high-throughput, low-latency inference using frameworks like VLLM and SGLang. Requires deep PyTorch expertise, systems programming, and performance engineering for reliable production deployment.