Machine Learning SoC Architect

What you'll do

• Analyze algorithms and workloads, define ASIC architecture, and assess throughput, memory bandwidth, latency, area, and power tradeoffs.
• Drive subsystem and chiplet-based SoC architecture; validate it using workloads, micro-benchmarks, simulation, and emulation.
• Coordinate with silicon, hardware, firmware, and software teams to deliver silicon and meet application performance goals; mentor architecture team members.

What they ask for

• Bachelor's degree in Computer Science, Computer Engineering, a relevant technical field, or equivalent practical experience.
• 12+ years of experience defining and delivering multiple high-performance ASICs into production, focused on architecture definition and performance analysis.
• Experience in ASIC performance modeling, microarchitectural analysis, or pre-silicon simulation for custom silicon or SoC designs.
• Proficiency in C++ and Python; experience analyzing data center, AI accelerator, or HPC workloads on custom silicon.

Nice to have

• Master's or PhD in Electrical Engineering, Computer Engineering, or a related field.
• Knowledge of power/performance tradeoffs, ML networks, or ML frameworks such as Pytorch; experience building performance modeling infrastructure for hyperscale data center ASICs.

Pay

$212,000/year to $294,000/year (base salary); bonus and equity amounts not stated.

Tools

C++, Python, Pytorch

AI focus

Architects custom machine-learning ASICs for data-center AI workloads, including workload mapping, performance modeling, and microarchitectural analysis.