MLOps Engineer, LLM Systems (Serving, GPU Kernels, Profiling)

Description: Join a leading AI lab's GenAI team to build foundational AI models. Focus on MLOps with experience in GPU kernel programming, performance profiling, debugging, and inference serving. Requirements: 2+ years of hands-on experience in ML systems, ML infrastructure, or GPU performance engineering. Practical experience in GPU kernel optimization, performance profiling, debugging distributed workloads, or serving large language models. Working experience with JAX and/or PyTorch; framework-level depth is a plus. Familiarity with modern accelerators (A100, H100, B200, TPU) and understanding of performance trade-offs. Strong written communication skills and ability to work 40 hours/week. Benefits: Competitive compensation of $90-$120 per hour. Opportunity to work on cutting-edge AI technologies and collaborate with experts.