Senior Director, Inference Products and Optimizations

Lead DigitalOcean’s Inference Engine organization to build and scale LLM inference products, including Serverless Inference, Dedicated Inference, Inference Router, Batch Inference, and Multimodal Inference. Own the inference serving stack and optimization/architecture layers, driving throughput, latency, and GPU utilization improvements. Recruit and coach engineers, partner cross-functionally on roadmap execution, and ensure production health, stability, and SLAs while institutionalizing observability, benchmarking, and tuning.