"tpu" Jobs

6 open tech roles matching “tpu”, taken straight from company career pages — not reposted from other job boards. Most in demand right now: XLA, C++, CUDA. Every listing is re-checked daily and closed roles are removed.

Showing 6 of 6 results

Member of Technical Staff, TPU Performance Engineering Visa

Join Inferact as a TPU performance engineer to optimize vLLM for Google TPUs, enhancing AI inference performance.

Inferact Singapore S$200k–S$400k/yr Published 2 months ago

JAX vLLM ML Pallas TPU

Flexible on stack

Apply →

Member of Technical Staff, TPU Performance Engineering Hybrid Visa

Join Inferact as a TPU performance engineer to optimize vLLM for Google TPUs, enhancing AI inference performance.

Inferact San Francisco $200k–$400k/yr Published 2 months ago

JAX vLLM ML Pallas TPU

Flexible on stack

Apply →

Member of Technical Staff, Kernel Engineering Visa

Join Inferact as a performance engineer to optimize vLLM, the fastest AI inference engine, working directly with hardware vendors.

Inferact Singapore S$200k–S$400k/yr Published 2 months ago

C++ FlashAttention CUDA LLVM rocprof

Flexible on stack

Apply →

Member of Technical Staff, Kernel Engineering Hybrid Visa

Join Inferact as a performance engineer to optimize vLLM, the fastest AI inference engine, working with cutting-edge hardware.

Inferact San Francisco $200k–$400k/yr Published 7 months ago

C++ CUDA LLVM ML MLIR

Flexible on stack

Apply →

Inference Engineering, Co-op

Join Inferact as a co-op student to work on cutting-edge AI inference systems in a hands-on engineering role.

Inferact San Francisco Published 3 days ago

C++ Triton JAX GPU programming CUDA

Flexible on stack

Apply →

Member of Technical Staff, Exceptional Generalist (Remote) Remote Visa

Join Inferact as a staff engineer to work on optimizing AI inference across the vLLM stack in a fully remote role.

Inferact Remote Published 7 months ago

C++ TensorRT-LLM SGLang CUDA vLLM

Flexible on stack

Apply →