GPU Infra Architect for AI Inference

DRW Holdings, LLC.; Montreal (administrative region); On-site; CAD 100,000 - 130,000; Full time

Job summary

A leading trading firm in Montreal is seeking an HPC Specialist to join their AI and Multi Asset Systematic Strategies team. This role involves deploying and optimizing GPU infrastructure for LLM workloads. The ideal candidate will have a degree in Computer Science or related field, along with over 5 years of experience in infrastructure engineering roles. Responsibilities include managing GPU-enabled Kubernetes clusters and collaborating with ML engineers. A commitment to innovation and performance optimization is essential for success in this role.

Qualifications

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

Responsibilities

• Deploy, maintain, and optimize GPU infrastructure for large-scale LLM inference workloads.
• Architect and implement distributed serving solutions for multi-node, multi-GPU model deployments.
• Manage GPU-enabled Kubernetes clusters for LLM and ML workloads.

Skills

GPU infrastructure

Model serving frameworks (vLLM, SGLang)

Kubernetes orchestration

Python scripting

Bash scripting

Infrastructure as code tools (Ansible, Terraform)

Monitoring and observability tools (Prometheus, Grafana)

Distributed systems knowledge

Education

Bachelor's or Master's degree in Computer Science, Systems Engineering, or related field

Job description

A leading trading firm in Montreal is seeking an HPC Specialist to join their AI and Multi Asset Systematic Strategies team. This role involves deploying and optimizing GPU infrastructure for LLM workloads. The ideal candidate will have a degree in Computer Science or related field, along with over 5 years of experience in infrastructure engineering roles. Responsibilities include managing GPU-enabled Kubernetes clusters and collaborating with ML engineers. A commitment to innovation and performance optimization is essential for success in this role.