FriendliAI
Open Positions at FriendliAI
17 open positions
Build and scale FriendliAI’s full-stack web platform for deploying models, managing organizations, monitoring workloads, and handling billing. This hands-on role spans backend systems, APIs, and polished developer-facing interfaces for AI infrastructure customers.
Own the architecture and evolution of FriendliAI’s large-scale Kubernetes infrastructure powering GPU-accelerated AI inference. This hands-on role focuses on cluster platforms, networking, autoscaling, reliability, and infrastructure automation.
FriendliAI is hiring a Cloud Infrastructure Software Engineer to architect and operate large-scale, GPU-accelerated Kubernetes clusters powering latency-sensitive AI inference. The role combines Kubernetes platform development, GPU scheduling, cloud networking, autoscaling, and production reliability.
Build the Python SDK, CLI, packaging pipelines, and developer tools that make FriendliAI’s inference and agent platform easy to integrate and use. This role focuses on ergonomic APIs, reliable releases, and an excellent developer experience for internal and external developers.
Design and optimize GPU kernels that power FriendliAI’s high-performance AI inference platform across NVIDIA and AMD hardware. This deeply technical role focuses on CUDA/C++, numerical precision, and maximizing inference speed at scale.
Optimize GPU kernels and core inference-engine infrastructure powering latency-critical generative and agentic AI workloads. You’ll work across compilers, runtimes, memory planning, and performance tooling to make production machine-learning inference faster and more efficient.
FriendliAI is hiring a contract-based Customer Success Engineer to help customers deploy, troubleshoot, and optimize generative and agentic AI workloads on its inference platform. The role combines technical onboarding, developer support, documentation, and collaboration with engineering.
Senior Backend Engineer responsible for building and scaling the production platform behind an AI inference service. The role owns APIs, business logic, data architecture, multi-tenant enterprise capabilities, and reliable multi-cloud operations.
Build production-ready AI agent features, APIs, and reference applications for document understanding, advanced RAG, and customer support automation. This hands-on role focuses on making open-source and multimodal models easy for developers to adopt.
Build the full-stack platform that customers use to deploy AI models, manage organizations, monitor workloads, and understand usage and billing. You’ll own features end to end across backend services, APIs, and polished web interfaces.
Unlock 7 More Matching Jobs
Create an account to view all jobs matching your criteria.
First to know
Discover the latest jobs before everyone else
Zero Spam
No ghost jobs, reposts, or sponsored listings
AI-powered filters
Find the most relevant jobs for you