Senior Hardware Performance Engineer for AI Accelerators

River AI; San Francisco (CA); On-site; USD 200,000 - 420,000; Full time

Benefits offered by this job

Health benefits

Dental and vision benefits

Unlimited PTO

Relocation support

Job summary

River AI seeks exceptional hardware performance engineers to architect, model, and correlate high‑performance custom silicon. You will develop simulators, own performance models, and collaborate across RTL, compiler, and software teams to optimize AI hardware for real-world models.

You will design high‑fidelity simulators, explore micro-architectural changes, profile AI kernels, and validate models against pre‑silicon environments, contributing to a leading-edge accelerator architecture.

Qualifications

• Bachelor’s degree in Electrical Engineering or Computer Engineering or Computer Science.
• 5+ years of practical industry experience with advanced process nodes (7nm or below).
• Expert proficiency in C/C++ or SystemC.
• Experience with compilers transforming code (LLVM/GCC/XLA) and high-performance kernels (CUDA/Triton) interacting with ISA.
• Expert knowledge in computer architecture of SoCs/CPUs/GPUs/AI accelerators.
• Experience profiling hardware with performance counters, profilers, and trace analysis tools.
• Highly collaborative mindset to co-design with engineers.

Responsibilities

• Design and implement high-performance hardware models using C++ and/or SystemC.
• Conduct micro-architectural exploration and study architectural changes and their impact on IPC and execution time.
• Characterize workloads by profiling AI kernels and software stacks to generate stress tests for models.
• Co-design with compiler and kernel teams to optimize software mapping to hardware.
• Validate performance models against RTL and emulators to ensure accuracy within tolerance.
• Identify and quantify system bottlenecks from ILP to bandwidth and utilization.

Skills

C/C++

SystemC

LLVM/GCC/XLA

Computer Architecture

Profiling Tools

Collaboration

Education

Bachelor’s degree in Electrical Engineering or Computer Engineering or Computer Science

Tools

QEMU models

Job description

River AI seeks exceptional hardware performance engineers to architect, model, and correlate high‑performance custom silicon. You will develop simulators, own performance models, and collaborate across RTL, compiler, and software teams to optimize AI hardware for real-world models.

You will design high‑fidelity simulators, explore micro-architectural changes, profile AI kernels, and validate models against pre‑silicon environments, contributing to a leading-edge accelerator architecture.