Software Engineer, Machine Learning Platform, New Grad - Quora (Remote)

Build and maintain the core infrastructure powering Quora's ML platform, ensuring high availability, scalability, and performance for models ranging from Large Recommendation Models to Large Language Models. Develop distributed systems and GPU model serving tools to optimize latency, throughput, and cost while contributing to PyTorch-first standardization and ML ecosystem modernization. Improve developer velocity by creating tooling that helps ML engineers develop, test, and deploy models more efficiently, and participate in the team's on-call rotation to resolve production issues. This role focuses on the intersection of Machine Learning, Distributed Systems, and GPU Serving performance, with no prior ML infrastructure experience required. You will join a team of senior engineers working on Quora's ranking infrastructure across serving reliability, ML engineer enablement, business impact, and cost efficiency.