Senior Product Manager, AI Inference Platform
Core
Building FAR AI, an AI inference platform for developers, AI-native companies, and enterprises to manage production workloads from model access to inference performance and billing.
Role type
Senior individual contributor Product Manager (AI Infrastructure)
Builds
AI inference platform covering model APIs, managed deployments, developer interfaces, routing, observability, usage, billing, and infrastructure control.
Domain
AI Infrastructure / GPU Cloud / Developer Platforms
Deliverable
production ML models
Required skills
AI inference platform experience, GPU cloud infrastructure, model serving, API design, developer experience, product strategy, technical requirements translation, product metrics, infrastructure economics, benchmarking, roadmap planning, cross-functional leadership
Preferred skills
vLLM, SGLang, TensorRT-LLM, Kubernetes, OpenAI-compatible APIs, enterprise AI controls
Technologies
vLLM, SGLang, TensorRT-LLM, Kubernetes, GPU infrastructure, OpenAI-compatible APIs
Responsibilities
Own major product areas end-to-end from discovery to launch; work directly with customers to understand deployment requirements and performance needs; translate technical constraints into clear PRDs and release plans; define inference platform strategy across APIs, routing, and observability; shape developer experience including API documentation and onboarding; partner on performance metrics like latency, throughput, and cost; define benchmark methodologies; prioritize features and protect the team from complexity; align cross-functional teams on product outcomes; track adoption and business performance metrics; monitor market intelligence to drive product decisions
Seniority
Senior, hands-on IC