freehire launches on Product Hunt on 26 August.

Follow →

Soniox

Discussion
1 job
Soniox
10 hours ago

Software Engineer, LLM Inference

HybridEuropeSenior
Slovenia

Optimize the vLLM-based LLM inference stack for low latency and high GPU utilization, writing CUDA/Triton kernels, tuning distributed execution, and profiling GPUs for a voice AI platform.

ai cuda distributed-systems llm pytorch +4 skills
 Sign in to see how this job matches your profile

Tailor your CV for this role?

We couldn't check your fit for this role — add a CV to your profile to see it next time.

A new version of freehire is available