AI Infrastructure Engineer

Hybrid
Posted Oct 16, 2026
1 position

Opens LinkedIn

Employment type: Full-time
Experience level: Senior · 5+ years
Minimum education: Bachelor’s degree
Posting language: English
Working hours: 40 hours per week
Seniority: Mid-Senior level

Job summary

Design and operate secure, reliable multi-cloud and on-premises infrastructure for large-scale AI workloads, including orchestrating deployments and benchmarking inference performance. Build monitoring and testing capabilities, optimize hardware utilization, and work with customers to deploy and integrate the company’s solutions.

Job details

Employment type: Full-time position, 40 hours per week, with direct employment by the client. Location: Remote-first role for candidates based in Canada. Travel requirement: Candidates must be available to visit the client’s office in Montreal approximately two to three times per quarter. Our company description Mission.dev is the next-gen staffing platform for software talent. We help you find, evaluate, and manage top software talent (contractors or direct hires) faster, smarter, and more efficiently. Powered by AI. Backed by real humans. About the client An AI infrastructure company specializing in inference optimization for large-scale models. The platform enhances token throughput and reduces latency by optimizing hardware utilization and decoding processes within a customer's cloud environment. The technology focuses on improving the efficiency of model serving without requiring changes to existing infrastructure or code, ensuring data privacy while reducing operational costs for organizations deploying open-source models. About the Role As a founding Senior AI Infrastructure Engineer, you will report to the Chief Technology Officer to design and operate large-scale infrastructure for AI workloads on public cloud and on-premises environments. You will be an individual contributor with significant influence, combining software engineering with deep systems expertise to build secure and reliable platforms. Your work will focus on enabling efficient model serving at scale, ensuring the infrastructure can support a massive number of concurrent users while maintaining high service quality and performance. What You'll Do Design and manage multi-cloud and on-premises infrastructure for internal and external workloads. Orchestrate large-scale deployments using infrastructure-as-code and container orchestration to support high user concurrency. Benchmark AI inference workloads to identify performance bottlenecks and optimize hardware utilization. Develop and maintain comprehensive monitoring systems to ensure high service quality and reliability. Collaborate with customers to deploy and integrate optimization solutions within their existing infrastructure. Build and maintain an internal laboratory for infrastructure testing and experimentation. What You Bring 5+ years of experience in AI infrastructure or systems engineering. Proficiency in Python and experience building and operating scalable APIs. Extensive experience with Kubernetes, Helm, Ansible, and Terraform. Proven track record of shipping large language model (LLM) serving systems in production environments. Experience with distributed computing frameworks such as Ray, RayClusters, or KubeRay. Demonstrated experience with agentic workflows. Bachelor’s degree in Computer Science or a related technical field. Compensation & Benefits Founding-engineer equity and direct ownership. Remote-friendly work environment. Visit the office 2-3x a quarter in Montreal. Access to extensive compute resources and specialized hardware for experimentation.

What you’ll do

Requirements

Requires at least five years of AI infrastructure or systems engineering experience, proficiency in Python and scalable APIs, and extensive experience with Kubernetes, Helm, Ansible, and Terraform. Candidates must have production LLM-serving experience, familiarity with Ray-based distributed computing and agentic workflows, and a bachelor’s degree in Computer Science or a related technical field.