Senior Inference Engineer
vCluster Labs · Cloud Computing
seniorRemote
Salary Range (USD)
$140k - $220k
Location
USA, Canada, Europe
Visa Support
Not mentioned
Funding Stage
VC-backed
Job Responsibilities
- • Production deployment/serving experience with vLLM, SGLang, or TensorRT-LLM
- • Hands‑on inference optimization (quantization, batching, caching, routing)
Required Skills
Experience with vLLMExperience with SGLangExperience with TensorRT-LLMStrong Python or Go skills
Engineering Culture & Tech Stack
vLLMSGLangTensorRT-LLMPythonGo
Raw Post
Show original text
vCluster Labs | Multiple Engineering Roles | REMOTE (US, Canada, Europe) | Full-time | $140k-$220k USD | $140k-220k CAD | €80K – €145K + Equity
vCluster Labs builds the software layer that turns hardware into a cloud. One platform to turn raw compute into every kind of cluster, for the teams building AI infrastructure and the customers they serve. We're a VC-backed startup in hyper-growth and fully remote.
We have several open roles, here are a few to highlight:
Senior/Staff Backend Engineer — Build controllers and operators at the core of the platform. Strong fit if you've authored Kubernetes controllers/operators from scratch using kubebuilder, controller-runtime, or client-go. Apply: https://www.vcluster.com/careers?ashby_jid=516c8859-83be-453... or https://www.vcluster.com/careers?ashby_jid=7a0a3f38-e7bf-407...
Senior Inference Engineer — Our first dedicated inference hire. Production deployment/serving experience with vLLM, SGLang, or TensorRT-LLM, hands-on inference optimization (quantization, batching, caching, routing), strong Python or Go.
Senior Application Security Engineer — Kubernetes internals from an exploitation/attack-surface perspective, hands-on container breakout and privilege escalation experience, real code-level security review, and threat modeling. Apply: https://www.vcluster.com/careers?ashby_jid=83c81a73-973f-406...
vNode Engineering Tech Lead — Build vNode, our tenant-isolation container runtime (Linux user namespaces and seccomp, no VM, no virtual kubelet). Container runtime internals (containerd, CRI-O, runc), Kubernetes node-level depth (kubelet, CRI layer), Linux isolation primitives (seccomp, user namespaces, cgroups). Apply: https://www.vcluster.com/careers?ashby_jid=c6a9423d-5f1f-4f4...
Full list of open roles: https://www.vcluster.com/careers
Feel free to reply here with any questions.
AI Risk Insights
No major risk signals detected.
Recent News
No recent updates
Data Source
Content parsed by LLM from Hacker News raw data. Confidence:HIGH