Datacenter & Agentic AI Workload Performance Analysis Engineer
$100k - $500k • Remote • Santa Clara, California, United States
Posted 16d ago
Job Location
Santa Clara, California, United States
Tech Stack
Remote Work Policy
Fully remote
Categories
Applied AI Engineer
About the job
Tenstorrent is seeking a Workload Performance Analysis Engineer to optimize the performance of next-generation RISC-V CPUs for modern datacenter and agentic AI workloads. This role bridges hardware and software, focusing on bringing real-world applications to RISC-V platforms, analyzing their behavior, and identifying opportunities for improved CPU performance, efficiency, and scalability. You will collaborate with CPU architects, designers, and software engineers to understand how demanding workloads interact with the CPU and translate these insights into architectural enhancements. Your work will directly impact CPU architecture and performance across cloud, enterprise, and emerging AI workloads.
Responsibilities
- Characterize the behavior of real-world applications on RISC-V platforms.
- Analyze workload performance to identify opportunities for CPU improvement.
- Collaborate with hardware and software teams to translate insights into architectural changes.
- Reduce large production workloads for performance modeling.
- Correlate simulation results with hardware behavior.
Requirements
- Strong background in CPU performance analysis, workload characterization, or computer architecture.
- Experience connecting software behavior to hardware performance.
- Understanding of modern CPU microarchitecture (pipelines, speculative execution, memory hierarchies, vector/SIMD).
- Proficiency in digging into complex workloads using profiling and simulation data.
- Comfort working across hardware and software layers (RTL to applications).
- Strong technical communication and collaboration skills.
- PhD in Computer Engineering, Electrical Engineering, Computer Science, or related field, with strong research/industry experience.
- Deep understanding of CPU architecture and RISC-V.
- Hands-on experience with performance analysis and simulation tools (Linux perf, strace, QEMU, CPU microarchitecture simulators).
- Strong programming skills in C/C++, Python, Bash/Shell, and assembly/intrinsic programming.
- Strong understanding of systems software (OS, virtualization, compilers, runtimes, GNU/RISC-V ecosystems).
Benefits
- Compensation ranges from $100k - $500k including base and variable compensation targets.
- Highly competitive compensation package and benefits.