Member of Technical Staff (TPM, Inference)

Join Perplexity, a leading AI company, as a Technical Program Manager. In this role, you will drive the development of our core inference platform, coordinating between model providers, engineering, and product teams. You will execute the roadmap for the inference platform, manage the onboarding and rollout of new models, and optimize performance metrics. The ideal candidate has strong technical judgment, experience with production LLM or ML inference, and thrives in a small, agile team.

• Execute the roadmap for the inference platform, including request handling, rate limits, quotas, and reliability.
• Coordinate onboarding, launch readiness, and rollout for new models and capacity, acting as the connective tissue between model providers and internal teams.
• Drive latency, throughput, uptime, and cost-efficiency as core execution metrics, surfacing tradeoffs between them.
• The ideal candidate has strong technical judgment, thrives coordinating across teams and external partners with competing timelines, and is energized by building the operating model for a function that doesn't have much precedent yet
• Comfort orchestrating across external partners and internal engineering teams with competing priorities and timelines
• Direct experience with production LLM or ML inference — understanding what makes serving fast, reliable, and cheap rather than just what a roadmap slide says about it
• Experience with data and metrics, and the judgment to surface difficult tradeoffs between latency, throughput, uptime, and cost
• Thrives in a small, agile team; has initiative and desire for ownership without much precedent to lean on
• 6+ years of combined technical program management or product management experience
• Strong experience with technical program management or product management in infrastructure, distributed systems, or ML/model-serving products