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

About the role

Join a leading AI lab’s GenAI team to work at the core of the AI revolution. You will help build foundational large‑language‑model (LLM) systems, focusing on serving, GPU kernel development, and performance profiling.

Key responsibilities

• Design, implement, and maintain serving infrastructure for advanced LLMs.
• Develop and optimise GPU kernels and profiling tools to maximise model performance.

Required skills

• MLOps
• LLM systems
• GPU kernels
• Profiling
• Software engineering