Datacenter & Agentic AI Workload Performance Analysis Engineer

Job Title

Datacenter & Agentic AI Workload Performance Analysis Engineer

Role Summary

Analyze and improve CPU performance of next-generation RISC-V processors across datacenter and agentic AI workloads. Work at the hardware–software boundary to bring real workloads onto RISC-V platforms, characterize their behavior, and translate findings into architectural recommendations.

Collaborate with CPU architects, RTL designers, software engineers, and compiler teams; outcomes will influence CPU architecture, RTL, emulation, and silicon used in cloud and enterprise environments. This position is remote based in North America.

Experience Level

Mid-level (Mid-Career). The posting does not specify years of experience.

Responsibilities

Core responsibilities include workload-driven performance analysis and collaboration with hardware and software teams.

• Port and run real-world datacenter and agentic AI workloads on RISC-V platforms and emulation environments.
• Profile and characterize workload behavior to identify performance, scalability, and efficiency bottlenecks.
• Reduce large production workloads into representative traces and benchmarks for architectural exploration and modeling.
• Correlate simulator/emulation results with hardware measurements to validate models and find discrepancies.
• Translate workload findings into actionable recommendations for CPU microarchitecture and RTL changes.
• Collaborate with architects, RTL designers, compiler and runtime teams to prioritize and implement improvements.
• Develop and maintain performance analysis scripts, benchmarks, and tooling.

Requirements

Must-have technical skills and experience; degree requirements are listed under Education Requirements.

• Deep understanding of CPU microarchitecture, including pipelines, speculative execution, memory hierarchies, and vector/SIMD concepts.
• Experience with RISC-V architecture and its software ecosystem.
• Hands-on experience with performance and simulation tools such as Linux perf, strace, QEMU, or CPU microarchitecture simulators.
• Strong programming skills in C/C++, Python, and shell scripting; experience with assembly or intrinsics.
• Solid knowledge of systems software: operating systems, virtualization, compilers, runtimes, and toolchains.
• Ability to work across hardware and software teams and to communicate technical results clearly to architects and engineers.
• Nice-to-have: experience with RTL, emulation platforms, benchmark development, or prior work on datacenter/AI workloads.

Education Requirements

PhD in Computer Engineering, Electrical Engineering, Computer Science, or a related field with strong research or industry experience in workload characterization, benchmark development, performance analysis, or simulation.

About the Company

Company: Tenstorrent

Headquarters: Austin, Texas, United States

Tenstorrent is a technology company focused on designing innovative computing solutions. They are known for their expertise in the development of advanced hardware, including ASICs and SoCs, aimed at enhancing performance and efficiency in various applications.