Mozilla's AI Platform team is seeking a Senior Machine Learning Engineer with a platform mindset to design, build, and operate the foundational infrastructure for AI experiences across products. The role involves owning model serving and inference workflows, optimizing GPU workloads, and ensuring reliability at global scale. You will collaborate with product, infrastructure, and security teams to enable fast iteration while meeting performance and privacy requirements.
Responsibilities
Design, build, and operate core AI platform components for training, deploying, and serving ML models in production.
Own model serving and inference workflows end-to-end, driving improvements in reliability, scalability, and performance.
Optimize inference systems for throughput, latency, and cost efficiency across CPU and GPU workloads.
Design and manage GPU-based inference and training workloads, including performance tuning and capacity planning.
Improve the model lifecycle: packaging, versioning, testing, validation, and deployment automation.
Implement observability practices (metrics, logging, tracing, alerting) for ML services.
Partner with product, infrastructure, security, and data teams to design scalable platform capabilities.
Mentor junior engineers and contribute to technical design discussions.
Requirements
Bachelor's degree with 4–6 years of relevant industry experience, or Master's with significant hands-on experience, or equivalent work experience.
