Similar Jobs
See allPerformance Architect, CPU Cluster
Tenstorrent
North America
Simulation
ML Systems Engineer, Inference
Runpod
Global
Python
VLLM
CUDA
CPU Performance Modeling (Lead & ICs)
Nuvacore
Global
C++
Python
Senior Compiler Performance Engineer
Azul
India
C++
Research Engineer - RL Infrastructure
Prime Intellect
Global
PyTorch
Distributed Training
CUDA
Work Overview:
- Optimize software workloads running on next-generation RISC-V platforms across modern datacenter and agentic AI use cases.
- Bring up and tune major runtimes, profile applications, and explore optimizations using RISC-V Vector/Matrix capabilities and custom instructions.
Who You Are:
- A performance engineer with hands-on experience optimizing software on RISC-V or another modern CPU architecture.
- Comfortable profiling complex systems, forming hypotheses, and iterating through optimizations using data.
What You'll Learn:
- How to optimize modern software stacks from application and runtime down to CPU microarchitecture and silicon.
- How runtime, compiler, memory, and concurrency decisions impact performance at datacenter scale.
Compensation:
- Compensation ranges from $100k - $500k including base and variable compensation targets.
- Offers vary based on experience, skills, education, background, and location.
Tenstorrent
Tenstorrent is leading the industry on cutting-edge AI technology, developing high performance RISC-V CPUs from scratch. Our diverse team of technologists values collaboration, curiosity, and a commitment to solving hard problems.