Member of Technical Staff (Software Engineer, GPU Cluster Infrastructure)

Job summary

Responsibilities

Perplexity serves hundreds of millions of queries a month, and every one of them fans out into multiple AI inference requests running in real time. Behind that sits a large GPU fleet spread across several cloud providers.

• Build a self-serve compute platform. Design and own the systems that let inference engineers and researchers launch training jobs and operate inference services without managing…
• Operate the GPU fleet. Own provisioning, lifecycle management, reliability, and capacity integration across providers, giving teams a consistent way to use compute regardless of…
• Solve for GPU scarcity. Build the scheduling and placement logic that finds available capacity across providers, packs it efficiently, and gets the right workload onto the right…
• Support two very different workloads. Keep long-running distributed training jobs healthy while simultaneously guaranteeing the availability and latency of production inference…
• Own the Kubernetes for GPU orchestration. Write the operators and CRDs, and manage many clusters across providers so the platform behaves the same everywhere we run.

What they're looking for

• Inference serving stacks: vLLM, SGLang, or TensorRT-LLM.
• Slurm or other HPC schedulers.
• GPU kernel work in CUDA or Triton — not required, but notable.
• High-speed interconnects: InfiniBand, RoCE, or RDMA in production.
• Observability for ML workloads: Prometheus, Grafana, or Weights & Biases.

Tech stack

• Kubernetes
• CUDA
• AWS
• GCP
• Go
• Rust
• C++
• vLLM