Machine Learning Engineer — Inference Optimization

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Machine Learning Engineer — Inference Optimization based in Australia. This role offers the opportunity to optimize the performance of advanced machine learning systems used in real-world production environments. You will work at the intersection of research and engineering, transforming cutting-edge models into fast, reliable, and cost-efficient solutions. Your work will directly impact model scalability, user experience, and the efficiency of AI-powered products. You will dive deep into performance optimization, from model architecture and GPU execution to large-scale inference infrastructure. Working with talented research, infrastructure, and product teams, you will help push the boundaries of what AI systems can achieve. This position is ideal for an engineer who enjoys solving complex technical challenges and building high-performance ML systems from the ground up.