Head of AI Infrastructure & LLM Systems

Role Overview & Executive Context

Directing large-scale GPU cluster infrastructure, distributed LLM inference pipelines, model optimization, and high-performance computing (HPC) engineering for next-generation generative AI models.

Key Responsibilities

• Architect scalable GPU compute clusters (H100/B200) for large language model pre-training
• Optimize inference latency, memory bandwidth, and distributed PyTorch / vLLM execution
• Lead a team of 15+ senior infrastructure, MLOps, and systems engineers
• Collaborate with AI Research Scientists to deploy foundation models to production

Required Qualifications & Leadership Experience

• 8+ years in distributed systems engineering and high-performance compute architecture
• Hands-on mastery of CUDA, Triton, PyTorch, Ray, Kubernetes, and InfiniBand networking
• Track record of operating 1,000+ GPU production clusters for LLM inference or training
• MS or PhD in Computer Science, Computer Engineering, or related quantitative field