AI Hardware Performance Engineer — SoC & Accelerators

River AI; Iowa; On-site; USD 200,000 - 420,000; Full time

Benefits offered by this job

Health, dental, and vision benefits

Unlimited PTO

Relocation support

Job summary

River AI is building high-performance hardware for AI workloads and seeks a Hardware Performance Engineer to model, simulate, and optimize our accelerator stack. You will develop C++/SystemC models, explore micro-architectures, and collaborate across RTL, compiler, and software teams to push IPC and efficiency in pre-silicon stages.

This role offers competitive compensation and equity, with visa sponsorship for exceptional candidates, and is based in the United States with options around Austin

Qualifications

• Bachelor's degree in Electrical Engineering, Computer Engineering or Computer Science with 5+ years of industry experience in advanced process nodes (7nm or below).
• Proficient in C/C++ or event-driven simulation environments like SystemC.
• Experience with compilers (LLVM/GCC/XLA) and high-performance kernels (CUDA/Triton) interacting with ISA.
• Strong knowledge of computer architecture for at least one chip style (SoCs/CPUs/GPUs/AI accelerators).
• Experience profiling hardware with performance counters and trace analysis tools.
• Collaborative mindset for cross-team co-design with engineers.

Responsibilities

• Simulator Development: design high-performance models of complex hardware using C++ and SystemC.
• Micro-architectural Exploration: run what-if studies on cache, branches, pipelines, and matmul shaping.
• Workload Characterization: profile AI kernels to create representative traces for stress-testing models.
• HW/SW Co-Design: optimize software mapping to hardware with compiler and kernel teams.
• Performance Correlation: compare models to RTL/pre-silicon emulators and ensure accuracy.
• Bottleneck Analysis: identify ILP limits and bandwidth bottlenecks affecting utilization.

Skills

Simulator development

Micro-architectural exploration

Workload characterization

HW/SW co-design

Performance correlation

Bottleneck analysis

Education

Bachelor's in Electrical/Computer Engineering or Computer Science

Tools

C++

SystemC

LLVM

GCC

CUDA

Triton

QEMU

Job description

River AI is building high-performance hardware for AI workloads and seeks a Hardware Performance Engineer to model, simulate, and optimize our accelerator stack. You will develop C++/SystemC models, explore micro-architectures, and collaborate across RTL, compiler, and software teams to push IPC and efficiency in pre-silicon stages.

This role offers competitive compensation and equity, with visa sponsorship for exceptional candidates, and is based in the United States with options around Austin