🕒 12 days ago
Deploy and operate production-grade generative AI inference workloads for enterprise customers, designing scalable Kubernetes architectures, troubleshooting performance issues, and integrating infrastructure into customer workflows.
Friendliai jobs
FriendliAI provides cloud inference for open-weight AI models and agent workloads.
🏢 Artificial Intelligence🤖 AI Inference Cloud
9 open roles at Friendliai
Sort jobs
🕒 18 days ago
Own enterprise sales for AI inference and serving solutions, building strategic relationships, managing technical proofs of concept, and closing high-value deals while shaping customer-informed product direction.
📅 Sep 16
Own the strategy and roadmap for an AI inference platform, translating complex infrastructure into customer-focused products while leading product initiatives, partnering with engineering and research, and developing the product team.
📅 Aug 12
Own and evolve the Kubernetes cluster platform behind a GPU-accelerated inference cloud, designing multi-tenant infrastructure, GPU scheduling, autoscaling, networking, and reliability for demanding production workloads.
📅 Apr 15
Own and evolve production backend services for an AI inference platform, building enterprise APIs, secure multi-tenant capabilities, and data systems while improving reliability and performance at scale.
📅 Apr 15
Build production-ready AI agent features, APIs, and Python reference applications for document understanding and other workflows, integrating open-source models and improving reliability, scalability, and developer adoption.
📅 Mar 27
Build and scale the full-stack platform for deploying AI models, monitoring workloads, and creating agent workflows, owning authentication, organization access, billing, and customer-facing experiences end to end.
📅 Mar 15
Design and optimize GPU kernels that accelerate AI inference across NVIDIA and AMD hardware, contributing to a production inference engine through low-level CUDA/C++ development, performance tuning, and quantization.
📅 Mar 15
Optimize GPU kernels and core inference infrastructure for generative AI workloads, improving performance across the software and hardware stack and supporting production-scale models.
Page 1 · 9 results