Remote RISC-V AI Performance Engineer Datacenter Workloads

Tenstorrent; California; Remote; USD 100,000 - 500,000; Full time

Job summary

Tenstorrent is seeking a Workload Performance Optimization Engineer to optimize software workloads on our next‑gen RISC‑V platforms. You will identify bottlenecks across runtimes, compilers, and hardware, and implement optimizations to improve throughput, latency, and energy efficiency on data center AI workloads.

Role spans Java, Python, C/C++, and Rust, with opportunities to profile real applications, explore Vector/Matrix capabilities, and contribute to AI-assisted automation of profiling and

Qualifications

• Master’s or PhD in Computer Engineering, Electrical Engineering, Computer Science, or a related field, with strong experience in performance optimization, computer architecture, compilers, or systems software.
• Hands‑on experience with runtime or compiler optimization, such as OpenJDK/JIT, LLVM, GCC, V8, Python, or equivalent systems.
• Strong understanding of CPU performance, memory hierarchies, concurrency, garbage collection, vector/SIMD optimization, and RISC-V architecture.
• Expertise with performance profiling and analysis tools such as Linux perf, runtime profilers, QEMU, tracing tools, and performance modeling environments.
• Strong programming skills in Java, Python, C/C++, and RISC-V assembly, with the ability to work effectively across multiple software layers.

Skills

Performance engineering

RISC-V experience

Profiling & optimization

Cross-layer collaboration

Education

MS/PhD in Computer Engineering/CS/EE

Advanced degree in CS/EE

Tools

Linux perf

QEMU

LLVM

GCC

Job description

Tenstorrent is seeking a Workload Performance Optimization Engineer to optimize software workloads on our next‑gen RISC‑V platforms. You will identify bottlenecks across runtimes, compilers, and hardware, and implement optimizations to improve throughput, latency, and energy efficiency on data center AI workloads.

Role spans Java, Python, C/C++, and Rust, with opportunities to profile real applications, explore Vector/Matrix capabilities, and contribute to AI-assisted automation of profiling and