Teams at FriendliAI

Own the vision, strategy, and roadmap for FriendliAI’s AI inference platform, including model serving, deployment, orchestration, APIs, and developer capabilities. Partner with engineering, research, enterprise customers, and go-to-market teams to improve inference performance, scalability, reliability, usability, and cost. Lead product initiatives from discovery through launch, establish product planning and measurement practices, and mentor Product Managers and Designers.

Build and scale FriendliAI’s web platform for AI model deployment, monitoring, inference, agent workflows, authentication, organization management, billing, and usage metering. Develop robust APIs and data models, integrate infrastructure and orchestration systems, deliver features through the UI, and improve reliability through testing, CI/CD, code reviews, and architecture improvements. The role requires strong Python and TypeScript skills, backend experience, and familiarity with cloud-native systems.

Design, build, and operate a multi-cluster, multi-tenant Kubernetes fleet for GPU inference. Extend Kubernetes with controllers/CRDs, implement GPU scheduling and autoscaling, own the network data plane, design cross-cluster connectivity and service mesh, drive reliability/SLOs, deliver IaC with Terraform/Helm/GitOps, and collaborate with platform, SRE, and security teams.