Member of Technical Staff (TPM, Inference)

Highlights

• Run one of industry's highest-throughput inference stacks serving Ask, API traffic.
• Lead day-zero model launches and rollouts across performance, infra, and product.
• Own reliability and observability for inference request handling and usage controls.

What they offer

• Equity

Ideal candidate

Technical program leader who thrives connecting engineering, product and external partners. Energized by high-throughput inference tradeoffs and building operating models from scratch with ownership.

Requirements

• Technical program or product management experience in infrastructure, distributed systems or ML/model-serving products
• Direct experience with production LLM or ML inference
• Comfort orchestrating external partners and internal engineering teams with competing priorities
• Experience using data and metrics to surface tradeoffs between latency, throughput, uptime and cost
• Thrives in small, agile teams with ownership and initiative
• 6+ years of combined technical program or product management experience