Jobs at FriendliAI

Design, build, and maintain agent APIs and production agent applications for document understanding, advanced RAG, and customer support automation. Integrate open-source models, collaborate with backend and infra for deployment and monitoring, and ensure APIs are robust, scalable, and developer-friendly.

Own and evolve core backend microservices for an AI inference platform: build production-grade APIs, multi-tenant SaaS features (auth, RBAC, billing), design OLTP/OLAP data models, collaborate on multi-cloud orchestration, ensure reliability/performance, and drive engineering quality through testing and CI/CD.

Design and optimize high-performance GPU kernels (GEMM, attention, routing) for AI inference across NVIDIA and AMD GPUs. Implement CUDA/C++ and low-level assembly code, build reduced-precision/quantized (FP8/FP4) kernels, benchmark cross-vendor performance, contribute to internal GPU libraries, accelerate multi-modal pipelines, and integrate next-generation GPU features into production.

Design, build, and maintain a scalable web platform and APIs for deploying and monitoring multimodal AI models and agent workflows. Collaborate with product, infrastructure, and design teams to optimize performance, ensure reliability, drive CI/CD and testing, and contribute to long-term architecture decisions for a cloud-native, multi-tenant SaaS system.

Lead end-to-end enterprise sales for FriendliAI's AI inference platform: generate pipeline, close high-value deals, run technical POCs, engage AI/ML communities, collaborate with engineering, and inform product roadmap.

Design, deploy, and operate large-scale LLM and multimodal inference architectures. Work hands-on with customer engineering teams to containerize, scale, monitor, and troubleshoot GPU-based inference workloads across Kubernetes, CI/CD, and hybrid/on-prem environments. Create Helm charts, Terraform modules, and observability tooling while delivering workshops and platform reliability insights.

Design, implement, and optimize GPU kernels, kernel compiler, memory planner, and runtime for low-latency generative AI inference. Analyze performance bottlenecks across hardware and software, collaborate with infrastructure teams, and maintain production profiling, benchmarking, and validation tooling while supporting new model architectures and multi-GPU strategies.