Software Engineer New Grad, Machine Learning Platform - Quora (Remote)
Core
Build and maintain core infrastructure for Quora's ML platform, serving hundreds of millions of users with high availability, scalability, and performance.
Role type
New Grad Software Engineer (ML Platform & Distributed Systems)
Builds
Distributed systems serving ML models (LRMs, LLMs), GPU model serving infrastructure, and developer tooling
Domain
Internet / Machine Learning Infrastructure / Distributed Systems
Deliverable
production ML models | infrastructure
Required skills
Python, Go, C++, distributed systems, GPU optimization, Kubernetes, cloud technologies
Preferred skills
ML frameworks (PyTorch/TensorFlow), low-level performance work (profiling/benchmarking), open-source contributions
Technologies
Python, Go, C++, PyTorch, Kubernetes/EKS, NVIDIA Triton, Ray, AWS
Responsibilities
Build distributed systems for serving ML models; optimize GPU model serving for latency and throughput; modernize feature store; build tooling to improve ML developer velocity; participate in on-call rotation for production issues
Seniority
Junior, New Grad