Senior Inference Engineer

As a Senior Inference Engineer at vCluster Labs, you are the first engineer we're hiring to own inference. You'll partner directly with our CTO to build the platform's inference layer from the ground up, taking models and turning them into a production-grade, query-to-response pipeline running m there, you will help lead the engineering direction of inference at vCluster, partnering with Product to shape what we build next as the space evolves.

As a Senior Inference Engineer, your role will include:

Deploying models to production: Take LLMs and put them into production across one or more machines on GPU infrastructure, owning the full pipeline from a customer's query to the served response.

Serving frameworks: Stand up and operate serving infrastructure using vLLM, SGLang, or TensorRT-LLM.

Optimizing for scale: Apply quantization, batching, caching, and routing to keep latency and cost in check as traffic grows.

Programming, not just configuring: Build real infrastructure in Python or Golang — this is an engineering role, not a research or data-science one.

Owning the roadmap: Build the first iteration alongside our CTO, then take the lead on the inference platform and partner with Product to decide what we build next.

This role could be a fit for you if you bring:

Production LLM serving experience: You've deployed and served LLMs using vLLM, SGLang, or TensorRT-LLM, ideally at a company built around inference at scale.

Inference optimization know-how: Hands-on experience with quantization, batching, caching, and routing, not just familiarity with the terms.

Hands-on programming experience: Strong engineering skills in Python or Golang, with real production code experience.

Communication: Strong communication skills, explaining technical concepts clearly to both engineers and non-technical stakeholders.

Familiarity with containerized environments (Docker, Kubernetes)

Hands-on generative AI experience with common ML frameworks (PyTorch, Transformers)

Good understanding of the GPU stack: CUDA, NCCL, drivers, and related libraries

Knowledge of model architectures and fine-tuning approaches

Experience with NVIDIA Dynamo

We’re the #1 platform for AI infrastructure, trusted by the world’s fastest-growing AI cloud builders. We’re a venture-backed startup that’s raised over $28M from top-tier investors including Khosla Ventures (first investor in OpenAI, Git Lab, Stripe, and Door Dash), and we’re in a hyper-growth phase looking for motivated people to join our team. Our headquarters are in San Francisco (Salesforce Tower), but our team is distributed around the globe with a remote-first culture.

We give AI Cloud providers and AI factories a hyperscaler-like experience on their own GPU infrastructure. Our platform runs the full stack an operator needs, from bare metal provisioning and node lifecycle management up through managed Kubernetes, Slurm, Ray, and inference clusters, so they can turn raw GPUs into cluster products they can sell in days instead of spending 12+ months building it themselves.

Today we power over 100,000 GPUs and 1 million CPUs across 50+ AI clouds and Fortune 500 companies, backed by a team of 40+ infrastructure engineers who build alongside our customers rather than just shipping them software.

We’re the company behind vCluster, the open source technology for tenant isolation on Kubernetes, with 11,000+ Git Hub stars and 40M+ tenant clusters created since 2021. Open source is part of our DNA. At Kube Con North America 2025, we launched our Infrastructure Tenancy Platform for AI, a Kubernetes-native framework built for running AI, ML, and GPU-intensive workloads anywhere, with an NVIDIA-validated reference architecture for DGX systems.

We offer the following benefits:

C…