Platform Product Reliability
Etched · San Jose
About this role
## About Etched Etched is building hardware for frontier intelligence. We co-design chips, racks, software, and manufacturing to deliver best-in-class throughput and latency across both prefill and decode workloads. Our first products are heavily focused on inference—backed by hundreds of millions from top-tier investors and staffed by leading engineers. ## Job Summary We’re seeking a highly technical, execution-focused **Platform Product Reliability Engineer** to lead reliability engineering across Etched’s server, rack, and datacenter platform products. This role owns **system-level product reliability** from architecture through fleet deployment. You’ll define reliability strategy, qualification methodologies, accelerated stress testing programs, failure analysis processes, and long-term reliability standards for complex AI infrastructure systems—ensuring every Etched product ships with the reliability profile enterprise and hyperscale customers demand. ## Key Responsibilities - Define and own the end-to-end reliability strategy for AI servers, accelerator platforms, rack systems, and datacenter infrastructure (design requirements → field deployment) - Establish reliability requirements, qualification standards, and validation methodologies across product generations - Build and institutionalize reliability engineering processes across the full lifecycle: - EVT / DVT / PVT qualification gates and exit criteria - Accelerated life testing (ALT) and accelerated stress testing (AST) - Environmental testing (temperature, humidity, altitude, contamination) - HALT / HASS for design margin and production screening - Vibration, shock, and transportation stress testing - Power cycling, thermal cycling, and long-duration soak testing - Lead root-cause investigations for reliability failures across development, manufacturing, and field deployment—driving corrective actions across hardware, firmware, thermal, and mechanical domains - Develop system reliability models (e.g., MTBF projections, FIT rate analysis, Weibull lifetime modeling, component derating, reliability growth tracking) - Partner early with Platform Engineering architects and design leads so reliability requirements shape decisions before they become expensive to change - Work with ODMs/JDMs/contract manufacturers/component suppliers to validate and enforce long-term platform reliability commitments - Build fleet reliability infrastructure (telemetry analysis pipelines, field feedback loops, monitoring frameworks) - Drive reliability signoff criteria and lead product release readiness reviews - Build and lead a high-performing product reliability engineering organization (hiring, developing, retaining technical talent) ## You may be a good fit if you have ### Must-have qualifications - BS, MS, or PhD in Electrical Engineering, Mechanical Engineering, Reliability Engineering, or a related technical field - 5+ years of reliability engineering experience in hardware-centric organizations (complex systems, not just component-level) - Experience leading reliability programs for one or more of: - AI accelerator or GPU-class compute systems - Hyperscale or cloud server infrastructure - Networking platforms, storage systems, or rack-scale infrastructure - Deep understanding of system-level failure mechanisms (thermal, power delivery, mechanical, connector/interconnect) and how design decisions impact long-term field reliability - Hands-on experience with FMEA, Weibull
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.