Senior AI Systems Performance Modeling Architect

Oho Group; San Francisco (CA); On-site; USD 180,000 - 300,000; Full time

Job summary

Oho Group in San Francisco, CA is seeking a Principal Performance Modeling Architect for AI systems to lead architecture-informed performance modeling before hardware realization. You will build analytical and simulation models to guide decisions across compute, memory, and interconnect, influencing silicon and software direction.

The role emphasizes strong Python/C++ skills, deep architectural knowledge, and collaboration with hardware, compiler, and runtime teams to translate model results

Qualifications

• Strong Python and/or C++ development experience.
• Experience building performance models for architectures.
• Deep knowledge of computer architecture and microarchitecture.
• Understanding compute pipelines, memory systems and data movement.
• Ability to translate model results into architectural decisions.
• Experience with GPUs, AI accelerators, LLM inference is a plus.

Responsibilities

• Build analytical and simulation-based performance models.
• Model processors, accelerators, memory hierarchies and interconnects.
• Analyze transformer inference across single-device and multi-accelerator systems.
• Evaluate latency, throughput, utilization, energy and cost trade-offs.
• Characterize workload behavior using traces and benchmarks.
• Identify architectural bottlenecks and propose measurable improvements.
• Partner with hardware, compiler, runtime and inference teams.
• Correlate models against simulation, emulation or silicon as the platform matures.

Skills

Python

C++

Performance modeling

Job description

Oho Group in San Francisco, CA is seeking a Principal Performance Modeling Architect for AI systems to lead architecture-informed performance modeling before hardware realization. You will build analytical and simulation models to guide decisions across compute, memory, and interconnect, influencing silicon and software direction.

The role emphasizes strong Python/C++ skills, deep architectural knowledge, and collaboration with hardware, compiler, and runtime teams to translate model results