Member of Technical Staff TPM Inference

You will execute the inference-platform roadmap and coordinate model-provider onboarding, launch readiness, capacity, and rollout. You will lead low-risk releases, track latency, throughput, uptime, and cost tradeoffs, and build dashboards, checklists, and operating mechanisms for predictable delivery.

Responsibilities

• Execute the inference-platform roadmap, including request handling, rate limits, quotas, usage controls, reliability, and observability.
• Coordinate model onboarding, launch readiness, and rollout with model providers, engineering, and product teams.
• Drive latency, throughput, uptime, and cost-efficiency metrics and surface tradeoffs.
• Run model-release and optimization programs, including day-zero launches.
• Lead cross-functional inference-stack changes from planning through launch and post-launch validation.
• Build release rituals, dashboards, and launch checklists.
• Partner with GPU capacity and compute teams on cost, capacity, and vendor constraints.

Requirements

• Experience in technical program management or product management for infrastructure, distributed systems, or ML and model-serving products.
• Direct production LLM or ML inference experience.
• Experience coordinating external partners and internal engineering teams.
• Experience with data and metrics and judgment about latency, throughput, uptime, and cost tradeoffs.
• 6+ years of combined technical program management or product management experience.

Benefits

• Equity
• Health insurance
• Dental insurance
• Vision insurance
• Retirement benefits
• Fitness benefits
• Commuter accounts
• Dependent care accounts