Technical Program Manager, Inference Platform

Perplexity; New York (NY); On-site; USD 170,000 - 265,000; Full time

Job summary

Perplexity is seeking a technical program manager to be the connective tissue between model providers, engineering, and product teams, driving our core inference platform forward.

You will orchestrate across external partners and internal teams to keep new models and capacity moving into production, while shaping the operating model and roadmap for the inference platform. Strong technical judgment and cross-team coordination are essential.

Qualifications

• Experience in infrastructure, distributed systems, or ML/model-serving products.
• Production LLM/ML inference experience for fast, reliable serving.
• Ability to coordinate with external partners and internal teams with competing priorities.

Responsibilities

• Execute roadmap for the inference platform including request handling, rate limits, quotas, and observability.
• Coordinate onboarding and rollout for new models with providers and internal teams.
• Drive latency, throughput, uptime, and cost-efficiency as core metrics.
• Lead release programs from planning through post-launch validation.
• Build release rituals, dashboards and launch checklists for low-risk releases.
• Collaborate with GPU capacity and compute teams on constraints and costs.

Skills

Technical PM

Cross-functional

Data-driven

Ownership

Initiative

Agile

Job description

Perplexity is seeking a technical program manager to be the connective tissue between model providers, engineering, and product teams, driving our core inference platform forward.

You will orchestrate across external partners and internal teams to keep new models and capacity moving into production, while shaping the operating model and roadmap for the inference platform. Strong technical judgment and cross-team coordination are essential.