Support the CEO by owning calendar strategy, communications, travel logistics, meeting preparation, leadership cadence, internal alignment, workflow automation, and strategic operational projects. The role requires independent judgment, discretion, strong communication, and end-to-end ownership in a fast-paced technology environment. This is a full-time, on-site position in Palo Alto, California.

Design, optimize, and scale low-latency, high-throughput inference serving systems for large multimodal models. Implement quantization, batching, speculative decoding, KV cache management, multi-GPU/multi-node parallelism, autoscaling, and load balancing while optimizing GPU utilization, reliability, and observability for production deployments and research evaluation.