Shape and own the QA strategy for FriendliAI’s inference platform, covering backend, frontend, model deployments, and novel validation for LLM inference quality.
Full-Stack Engineer role at FriendliAI to build the web platform and APIs that power deployment, monitoring, and developer-facing tools for multimodal AI workloads.
Senior Backend Engineer needed to design and operate production-grade APIs and backend systems for a fast-moving AI inference platform serving enterprise deployments.
FriendliAI seeks a Python Engineer to design and ship SDKs, CLIs, and developer tools that make integrating with its inference platform fast, reliable, and easy.
Technical Writer needed to create developer-focused docs, customer guides, and marketing content that demystify FriendliAI's high-performance AI inference platform.
Work as an Inference Engine Engineer at FriendliAI to design high-performance GPU kernels and core runtime components that power latency-critical, production-scale generative AI systems.
