About this role
Inference Engineer at Cartesia. Location: San Francisco, California, United States. Role: Design inference stack, Collaborate with researchers, Build monitoring infrastructure Requirements: Engineering-focused; strong experience with large-scale distributed systems and inference pipelines. Category: Engineering Seniority: Mid Level Tools: CUDA, Triton, Transformers, Monorepos, Distributed Systems Commitment: Full Time Workplace: Onsite Languages: English