Member of Technical Staff (TPM, Inference)
Perplexity · San Francisco
About this role
**Member of Technical Staff (TPM, Inference)** **About the Role** Perplexity is seeking a technical program manager to serve as the connective tissue between model providers, engineering, and product teams. You'll drive the core inference platform forward—one of the highest-throughput inference stacks in the industry. **Key Responsibilities** • Execute the inference platform roadmap (request handling, rate limits, quotas, usage controls, reliability, observability) • Coordinate model onboarding, launch readiness, and rollout between providers and internal teams • Drive latency, throughput, uptime, and cost-efficiency as core metrics • Run the operating model for model-release and optimization programs • Lead cross-functional delivery for inference-stack changes from planning through post-launch validation • Build mechanisms for predictable releases (rituals, dashboards, checklists) • Partner with GPU capacity and compute teams on execution decisions **Required Qualifications** • 6+ years of technical program management or product management experience • Strong background in infrastructure, distributed systems, or ML/model-serving products • Direct production LLM or ML inference experience • Proven ability to orchestrate across external partners and internal teams with competing priorities • Strong data and metrics judgment; ability to surface tradeoffs between latency, throughput, uptime, and cost • Thrives in small, agile teams with ownership and initiative **About Perplexity** Perplexity's mission is to power curiosity through a cycle of learning, building, and integrating—enabling curious people to drive change in the world.
Listing freshness
CronJobs last confirmed this listing 15h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.