GPU Infrastructure Engineer for AI Inference & Serving

P2P; Montreal (administrative region); On-site; CAD 90,000 - 120,000; Full time

Job summary

A diversified trading firm is seeking an HPC Specialist to join their AI and Multi Asset Systematic Strategies team. This role focuses on building and managing GPU infrastructure for AI and ML workloads. Candidates should have strong experience in DevOps, GPU technology, and Kubernetes orchestration. A Bachelor’s or Master’s degree in a related field is required, along with a proven track record in optimizing deep learning workloads. This position is based in Montreal, Quebec.

Qualifications

• 5+ years in DevOps, SRE, or infrastructure engineering roles.
• Strong experience with model serving frameworks and GPU driver management.
• Hands-on experience optimizing deep learning workloads on GPU clusters.

Responsibilities

• Deploy, maintain, and optimize GPU infrastructure for large-scale LLM inference workloads.
• Manage GPU-enabled Kubernetes clusters for LLM and ML workloads.
• Collaborate with ML engineers on model performance and inference acceleration.

Skills

GPU infrastructure

Kubernetes orchestration

Python

Bash scripting

Deep learning workloads

Distributed systems

Monitoring tools

Education

Bachelor's or Master's degree in Computer Science

Tools

Ansible

Terraform

Prometheus

Grafana

vLLM

SGLang

Job description

A diversified trading firm is seeking an HPC Specialist to join their AI and Multi Asset Systematic Strategies team. This role focuses on building and managing GPU infrastructure for AI and ML workloads. Candidates should have strong experience in DevOps, GPU technology, and Kubernetes orchestration. A Bachelor’s or Master’s degree in a related field is required, along with a proven track record in optimizing deep learning workloads. This position is based in Montreal, Quebec.