Member of Technical Staff (TPM, Inference)
Core
Orchestrates the inference platform roadmap, coordinating between model providers, engineering, and product teams to ensure smooth model onboarding, capacity scaling, and production reliability.
Role type
Senior technical program manager (inference platform)
Builds
High-throughput inference stack serving Ask, Computer, and API traffic for first-party and third-party models
Domain
AI/ML infrastructure, distributed systems, model serving
Deliverable
production ML models
Required skills
Technical program management, production LLM inference, cross-functional orchestration, data and metrics analysis, infrastructure systems, cost-efficiency optimization, release management, vendor coordination
Preferred skills
Experience with GPU capacity planning, operating model design for new functions, agile team leadership
Technologies
LLM inference stacks, distributed systems, GPU compute infrastructure
Responsibilities
Execute the inference platform roadmap including request handling, rate limits, and usage controls; Coordinate model provider onboarding and launch readiness; Drive latency, throughput, uptime, and cost-efficiency metrics; Run operating models for model-release and optimization programs; Lead cross-functional delivery for inference-stack changes; Build release mechanisms like rituals and dashboards to ensure low-risk deployments.
Seniority
Senior, hands-on IC
