Infrastructure Engineer

We’re supporting a client with the recruitment requirement outlined below. If your recruiting expertise and networks align with the role, please 'apply', to express your interest.

Once approved to work on the opportunity, you’ll receive the full brief, including the client name, role details and commercial terms.

Role Details

Company: US-headquartered AI infrastructure company

Location: San Francisco, California

Employment Type: Full-time

Work Arrangement: In-office, five days per week

Experience: 5+ years in infrastructure engineering

Base Salary: $350,000–$450,000

Visa: Transfers possible

Relocation: Considered for exceptional candidates

About the Company

An innovative, venture-backed AI company building high-performance infrastructure for serving large language models (LLMs). Its platform delivers ultra-fast inference across multiple accelerator architectures and cloud environments, supporting demanding AI research and engineering workloads.

About the Role

The company is seeking a senior infrastructure engineer to own and scale its production LLM inference platform. This is a highly technical, hands-on role focused on Kubernetes, GPU infrastructure, multi-cloud deployments, and reliability for latency-sensitive AI workloads.

Responsibilities

• Build and operate production Kubernetes infrastructure across AWS, GCP, and GPU cloud providers.

• Optimize and troubleshoot LLM inference serving systems and GPU infrastructure.

• Debug NVIDIA drivers, CUDA, NCCL, and high-performance networking issues.

• Support deployments across NVIDIA GPUs and other accelerator architectures.

• Build observability, automated failover, and reliability systems.

• Collaborate with model optimization engineers to improve inference performance.

• Own complex production issues and drive solutions independently.

Requirements

• 5+ years of infrastructure engineering experience, currently at Staff level or above in an IC role.

• Strong production Kubernetes experience across multiple cloud environments.

• Hands-on experience with production LLM inference platforms.

• Expertise in NVIDIA GPU systems, CUDA, NCCL, and node-level debugging.

• Experience with inference frameworks such as vLLM, SGLang, TensorRT-LLM, or Dynamo.

• Knowledge of high-performance networking, such as InfiniBand, RDMA/EFA, or MPI.

• Experience with observability and reliability for latency-sensitive services.

Interview Process

• Initial screening call.

• Technical interview.

• Additional technical assessment, if required.

• Final interview, potentially onsite.