About this role
Software Engineer, ML Infrastructure at Realm Labs. Location: Sunnyvale, California, United States. Role: deploy models, optimize performance, scale deployments Requirements: 5+ years in ML infrastructure or production ML roles; strong software engineering; deep hands-on with LLM inference infra; GPU optimization; Linux-based production environments. Category: Engineering Seniority: Senior Level Tools: PyTorch, TensorFlow, vLLM, TensorRT, TensorRT-LLM, Triton Inference Server, SGLang, CUDA Commitment: Full Time Workplace: Onsite Languages: English