Senior Director, Inference Products and Optimizations

Lead the Inference Engine organization to build and scale DigitalOcean’s LLM inference product suite, including serverless inference, dedicated inference, inference router, batch inference, and multimodal inference. Drive deep technical strategy across inference serving, model optimization, and architecture layers to deliver high-performance, cost-efficient systems. Recruit and coach engineering leaders, partner cross-functionally on roadmap execution, ensure production health and SLAs, and institutionalize benchmarking, observability, and auto-tuning.