AI ML Performance Engineer

Role: AI ML Performance EngineerLocation: Bellevue, WA (Hybrid)Employment Type: ContractAbout the Role We are looking for an experienced AI/ML Performance Engineer to design and execute high-intensity stress workloads for next-generation AI platforms. This role focuses on identifying performance bottlenecks, improving system stability, and enabling scalable, production-ready AI infrastructure.Key ResponsibilitiesDesign and implement high-intensity stress workloads using PyTorch and TritonAnalyze system performance to identify bottlenecks, stability issues, and performance cliffsDevelop workloads targeting large GEMMs, attention mechanisms, MoE-like architectures, mixed precision, and long-running executionsBuild custom Triton kernels to stress hardware execution units, memory hierarchies, and synchronization pathsCreate scalable test harnesses across problem size, number of devices, and runtime durationIntegrate workloads with profiling, monitoring, and failure triage toolsCollaborate with platform, firmware, and SDK teamsProvide documentation and reproducible scripts for lab and CI environmentsRequired SkillsStrong experience in performance testing and analysis (test result analysis, server stats, bottleneck identification, tuning, and recommendations)Proficiency in PythonScripting experience using Shell or PowerShellExperience with PyTorch and/or TritonNice to HaveExperience with AI hardware platforms or simulatorsExposure to distributed systems and multi-device workloads