GenAI Platform Architect: Multi-GPU & LLM Inference

Quantiphi; United States; On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Healthcare benefits

Professional growth opportunities

Job summary

Quantiphi is seeking an Architect - Platform Engineer to design, optimize, and scale GenAI infrastructure for multi-GPU workloads. The role emphasizes GPU profiling, distributed training, and high-performance compute environments.

You will collaborate with data science, MLOps, and application teams to deploy cutting-edge AI solutions. Responsibilities include implementing scalable LLM and GenAI pipelines, managing Slurm clusters, and delivering reusable IaC templates using Terraform and Helm.

Qualifications

• Experience with Slurm-based clusters or distributed training environments.
• Deep knowledge of container orchestration (Kubernetes/OpenShift) in production.
• Strong Linux systems background and multi-GPU performance tuning.
• Hands-on experience deploying GenAI workloads (LLMs, RAG, fine-tuning).
• Familiarity with IaC tools (Terraform, Ansible) and cloud GPU platforms.

Responsibilities

• Design scalable GenAI infrastructure for multi-GPU workloads.
• Profile, benchmark, and optimize GPU performance for distributed training.
• Manage compute scheduling with Slurm and container platforms (Kubernetes/OpenShift).
• Develop reusable infrastructure templates (Terraform, Helm) for GenAI deployments.
• Collaborate with data science and MLOps teams to deploy models in prod.

Skills

Distributed training

Multi-GPU optimization

GenAI workloads

Linux performance tuning

NVIDIA GPU ecosystem

Cloud GPU environments

MLOps collaboration

Education

Bachelor's degree in CS/EE or related field

Tools

Slurm

OpenShift

Kubernetes

Terraform

Ansible

NVIDIA CUDA

NCCL

TensorRT

Job description

Quantiphi is seeking an Architect - Platform Engineer to design, optimize, and scale GenAI infrastructure for multi-GPU workloads. The role emphasizes GPU profiling, distributed training, and high-performance compute environments.

You will collaborate with data science, MLOps, and application teams to deploy cutting-edge AI solutions. Responsibilities include implementing scalable LLM and GenAI pipelines, managing Slurm clusters, and delivering reusable IaC templates using Terraform and Helm.