About this role
Build and optimize TPU backends, compiler integrations, and runtime paths to make vLLM a first-class inference engine on Google TPUs. Improve production-relevant model serving by optimizing kernels and benchmarking latency and throughput.
Requires a Bachelor's degree in CS or a related field and hands-on experience optimizing TPU workloads using JAX, XLA, or Pallas. Candidates should have deep knowledge of TPU execution, memory behavior, and ML kernel optimization.
What they're looking for
TPU Performance EngineeringJAXXLAPallasML Kernel OptimizationPerformance ProfilingBenchmarkingLLM Inference Systems
Frequently asked questions
What does a Member of Technical Staff, TPU Performance Engineering at Inferact do?
Build and optimize TPU backends, compiler integrations, and runtime paths to make vLLM a first-class inference engine on Google TPUs. Improve production-relevant model serving by optimizing kernels and benchmarking latency and throughput. Requires a Bachelor's degree in CS or a related field and han…
What skills does this Member of Technical Staff, TPU Performance Engineering role need?
Key skills for this role include TPU Performance Engineering, JAX, XLA, Pallas, ML Kernel Optimization, Performance Profiling.
How much does a Member of Technical Staff, TPU Performance Engineering at Inferact pay?
The employer did not list a salary for this role. Most similar Singapore roles publish their band on the job page.
Is this Member of Technical Staff, TPU Performance Engineering role remote, hybrid, or on-site?
This role is on-site, based in Singapore.
How do I apply for this Member of Technical Staff, TPU Performance Engineering role?
You can apply directly on Inferact's careers page. ApplyLah can tailor your résumé and cover letter to this exact role in seconds first.