Design and operate low-latency, high-throughput services for Yobi’s real-time ML-based ad platform, working closely with product and data teams to deliver reliable, scalable systems.
Yobi is hiring an ML Engineer (Inference/Serving) to build and operate low-latency, production-grade model serving systems that turn behavioral models into reliable, observable services.
Lead the design and implementation of Yobi’s real-time ML-based advertising stack, owning a major product area and mentoring engineers while building high-throughput, low-latency systems.
Lead the design and operation of Yobi’s data platform and pipelines to scale privacy-first behavioral AI while influencing engineering conventions and reliability at the company level.
