Sr./Staff TPM - Inference Capacity

Highlights

• Lead capacity planning and fleet strategy for world-leading AI inference service.
• Own 6/12/26-week rolling capacity model across every inference cluster.
• Drive new datacenter bring-up and production readiness for inference scale.

Ideal candidate

Experienced TPM who thrives at the intersection of engineering, product and operations and loves turning complex capacity tradeoffs into clear plans. Data-driven owner excited to maximize utilization of cutting-edge AI infrastructure at scale.

Requirements

• Program management or product operations experience in cloud infrastructure, large-scale ML serving, or hyperscaler capacity planning
• Experience leading large cross-functional programs across Engineering, Product and Operations
• Comfort with inference serving stack including model replicas, batching, prefill/decode, KV cache and accelerator scheduling
• Strong data fluency with SQL, Grafana, and basic Python or Flux to self-serve analysis
• Track record running recurring cross-functional rituals with senior engineers and leadership
• Direct experience with AI accelerator fleet operations such as Habana, TPU pods, Inferentia, Trainium