Netpreme is seeking a skilled engineer to own the inference-serving stack for frontier LLM workloads. You will optimize and operate distributed inference pipelines, working with vLLM, SGLang, and TensorRT-LLM, while coordinating with hardware and systems teams.
You’ll build benchmarks, tune performance, and drive production readiness with Kubernetes, NVIDIA Dynamo, Helm, and Ansible, in a fast-moving startup setting.
#J-18808-Ljbffr
The following role is for a LLM Inference Systems Engineer with Netpreme.
Please review the full job details above before applying.
If your experience matches this role, we encourage you to apply.
All applications are reviewed carefully by our team.
The position is based in Boston, MA, United States.
This opportunity is part of our work in IT & Technology.
The advertised compensation is 170.000 - 210.000.
We aim to respond to suitable candidates as soon as possible.