Telnyx · Global cloud connectivity, IP network, and AI inference infrastructure
Inference Infrastructure Architect (Remote)
ChinaEngineeringPosted 2026-09-16
Where you can live
Open to people living in China.
Listed location: China - Remote
Taken from the location the company listed. Confirm in the posting before you apply.
What the job is
Operates and expands a bare-metal GPU fleet for inference, and builds serverless and dedicated model serving on the open-source stack.
What they ask for
- Owned production LLM serving under meaningful traffic and latency constraints
- Operated Kubernetes on GPU fleets end to end
- Deep operational command of vLLM or SGLang
- Performance engineering with engine and DCGM metrics and roofline reasoning
- Python and Go for automation, with Linux, networking and storage depth
Nice to have
- Fine-tuning and RL infrastructure experience (LoRA pipelines, evaluation, champion/challenger rollout)
- Real-time voice latency work with sub-second time-to-first-token
- Multi-region deployments and data-residency requirements
This is a summary written by software from the company's posting. The posting is the source.
More remote jobs at Telnyx