HPC Specialist (AI/ML)

Location: Montreal, Canada

Company

hirify.global is a diversified trading firm that combines sophisticated technology and trading expertise across global financial markets, with additional strategies in real estate, venture capital, and cryptoassets.

What you will do

• Deploy, maintain, and optimize GPU server fleets for large-scale LLM inference workloads.
• Architect distributed serving solutions for multi-node, multi-GPU model deployments.
• Manage GPU-enabled Kubernetes clusters and configure networking, load balancers, firewalls, and inter-node communication.
• Implement storage solutions for model weights and inference caches.
• Troubleshoot performance bottlenecks across hardware, drivers, networking, and application layers.
• Collaborate with ML engineers on model profiling, inference acceleration, monitoring, capacity planning, and incident response.

Requirements

• Bachelor’s or Master’s degree in Computer Science, Systems Engineering, or a related field.
• 5+ years of experience in DevOps, SRE, or infrastructure engineering.
• Strong experience with GPU infrastructure, GPU driver management, and model serving frameworks such as vLLM and SGLang.
• Hands-on experience optimizing deep learning inference or training workloads on GPU clusters.
• Deep Linux systems knowledge, including networking, storage optimization, and Kubernetes orchestration.
• Experience with Ansible, Terraform, or similar infrastructure-as-code tools, plus Python and Bash scripting, distributed systems, TCP/IP, HTTP/2, load balancing, Prometheus, and Grafana.

Culture & Benefits

• Work in an environment emphasizing autonomy, innovation, integrity, curiosity, and challenging consensus.
• Collaborate with AI, ML, and systematic strategies specialists on infrastructure supporting global trading activities.