AI Inference Performance Visibility Lead

Etched; San Jose (CA); Hybride; USD 180 000 - 240 000; Plein temps

Avantages offerts par ce poste

Medical, dental, and vision packages

Housing subsidy

Relocation support

Wellness benefits

Lunch and dinner in office

Unlimited compute budget

Résumé du poste

Etched is pioneering an AI hardware frontier in San Jose, seeking a Head of Performance Visibility to define how performance is understood across next‑generation AI accelerators. You will define metrics connecting hardware signals to distributed workloads, shaping cross-layer event correlation, time-alignment, and scalable reasoning across nodes and racks.

This role sits at the intersection of hardware, drivers, runtimes, and ML infrastructure.

Qualifications

• Deep experience building complex systems at the intersection of hardware and software.
• Built profiling, tracing, or observability systems.
• Translate raw hardware signals into scalable telemetry and analysis infrastructure.
• Experience correlating time-series events across distributed systems.
• Systems programming expertise (C++ or Rust) near hardware/runtime.
• Experience designing distributed tracing or observability platforms at scale.
• Experience with time synchronization and event alignment across devices/hosts.

Responsabilités

• Define architectural approach for collecting telemetry across CPUs, drivers, interconnects, and accelerators.
• Design scalable models for correlating performance events across device and host boundaries.
• Align hardware counters, runtime activity, and workload semantics across model-layer execution.
• Implement time synchronization and trace-alignment strategies across multi-device systems.
• Define structured counter taxonomies and derive performance models.
• Influence instrumentation strategy for future hardware generations.
• Build tools to identify bottlenecks among multi-accelerator workloads.
• Build cluster-scale performance analysis for distributed inference across data center networks.
• Contribute to analysis engines and developer-facing tooling.
• Shape how performance intelligence is surfaced to engineers debugging large-scale AI systems.

Connaissances

Hardware-software systems

Profiling/observability

Distributed systems

C++ or Rust

Distributed tracing

Cross-functional leadership

Timestamp alignment

Performance modeling

Outils

Profiling tools

Observability tooling

Time synchronization

Telemetry systems

Description du poste

Etched is pioneering an AI hardware frontier in San Jose, seeking a Head of Performance Visibility to define how performance is understood across next‑generation AI accelerators. You will define metrics connecting hardware signals to distributed workloads, shaping cross-layer event correlation, time-alignment, and scalable reasoning across nodes and racks.

This role sits at the intersection of hardware, drivers, runtimes, and ML infrastructure.