Top Tech Jobs & Startup Jobs in Seattle, WA

Lead the architecture and hands-on development of distributed AI inference runtime systems. Responsibilities include scheduling, batching, KV-cache and memory management, distributed execution, kernel optimization, profiling, benchmarking, and performance analysis. Enable new model architectures, improve latency and throughput, develop validation and safe-rollout systems, and collaborate with infrastructure, compiler, hardware, cloud, and research teams. Mentor engineers and establish performance-engineering practices for Arm’s production AI platform.

Designs, builds, and operates large-scale AI compute infrastructure for training, fine-tuning, evaluation, and inference. Responsibilities include managing Kubernetes clusters, enabling CPU and GPU systems, optimizing scheduling and capacity, troubleshooting distributed infrastructure, and automating provisioning, upgrades, monitoring, and maintenance. The role partners closely with AI researchers and engineers to improve infrastructure reliability, scalability, performance, and developer productivity.

Lead the architecture and development of highly available cloud services for AI inference. Build Kubernetes controllers and platform capabilities for workload scheduling, scaling, recovery, deployment, and lifecycle management. Improve reliability, observability, performance, and resource efficiency through production readiness reviews and incident-driven improvements. Guide complex technical initiatives, mentor engineers, resolve infrastructure issues, and align architecture across AI compute, runtime, and product teams.

Leads architecture and hands-on development of distributed AI inference runtime capabilities, including scheduling, batching, KV-cache management, memory allocation, kernel optimization, model execution, and performance benchmarking. Partners with infrastructure, compiler, hardware, cloud, and research teams to improve latency, throughput, reliability, and resource efficiency. Provides technical leadership, conducts reviews, mentors engineers, and establishes performance-engineering practices for production AI workloads.

Build foundational platform software, runtime infrastructure, APIs, SDKs, and developer tooling for on-device physical AI workloads. Develop reliable deployment, lifecycle management, observability, and diagnostics systems under edge constraints. Optimize performance across CPUs and AI accelerators while creating stable abstractions over AI frameworks, models, and hardware. Collaborate with architects, product managers, and AI engineers on production-ready platform capabilities, reference implementations, documentation, and workflows.

Design, build, and operate large-scale AI compute infrastructure for training, fine-tuning, evaluation, and inference. Manage Kubernetes clusters, workload scheduling, accelerator enablement, networking, storage, monitoring, and capacity. Troubleshoot complex application, cloud, cluster, and hardware issues while improving reliability, performance, scalability, and developer productivity. Partner with AI teams to automate provisioning, upgrades, monitoring, and maintenance.

Design and implement scalable platform services, runtimes, and developer tooling for deploying and managing AI workloads on Arm-based edge devices. Build abstractions, observability, and performance optimizations across heterogeneous hardware while collaborating with architects and AI engineers to produce robust, maintainable systems and SDKs for on-device AI.