High-Performance AI Inference Platform Engineer

DRW is seeking an AI Inference Platform Engineer to build, operate, and optimize systems that serve large language, vision, multimodal, and embedding models across DRW. You'll own the serving platform end-to-end, onboarding models, measuring quality and performance across configurations, and scaling workloads for multiple tenants. This role requires hands-on GPU literacy and deep experience with modern inference runtimes, KV cache architectures, and multi-tenant scheduling, all within a trading