
Senior Director, Inference Products and Optimizations
Lead and grow a high-performing engineering team to build and scale LLM inference products (Serverless, Dedicated, Inference Router, Batch, Multimodal). Own model-serving and optimization layers (vLLM, SGLang, LLM-D), drive performance and cost-efficiency at scale, ensure production health and observability, and collaborate cross-functionally on product roadmaps. Role expects 10+ years software engineering experience with 6+ years in technical leadership.













