Principal Software Engineer, Machine Learning Infrastructure

Overview As Principal Software Engineer in Snap’s ML Inference team, you shape the technical direction of scalable ML inference platforms and drive high-impact architectural decisions. You’ll partner across teams to translate product needs into robust, available systems, while championing operational excellence and cost effectiveness. You’ll lead by example, mentoring engineers and influencing the company’s technical trajectory. This role offers the chance to advance cutting-edge AI features at scale in a privacy-conscious, collaborative culture. Compensation / Benefitspaid parental leavecomprehensive medical coverageemotional and mental health supportequity in RSUscompetitive compensation ResponsibilitiesOversee technical strategy and architecture in ML Inference Platform servicesDesign, implement, and scale critical engineering components and services to support ML inference and deploymentCollaborate across teams to translate product requirements into effective solutionsAdvocate for availability, scalability, operational excellence, and cost managementProvide technical direction that influences the entire company Key requirementsBachelor in a technical field or equivalent experience10+ years of post-Bachelor’s software development experience (or advanced degree with 9+ years; PhD with 6+ years)2+ years of technical leadership or domain-expert experienceExperience architecting and developing large-scale distributed systems and high-throughput RPC servicesProven track record of operating highly-available systems at scaleAbility to learn new concepts and apply them in workStrong collaboration and mentorship skillscollaborationmentorshipproblem solving in ambiguous contextsTensorFlowPyTorchKubernetes