Infrastructure Engineer

Company Description CarbonForge is a Mila-backed startup focused on making efficient AI the default for teams serving open-weight models. The company delivers optimized inference containers that bundle the model, tuned for specific workloads, and an additional optimization layer to unlock more performance from GPUs. CarbonForge integrates into existing compile and deploy paths, searching for Pareto-optimal operating points that lower energy use per token while maintaining model quality. The platform outputs reproducible before/after benchmarks and deployment configurations that meet SLA targets with reduced power consumption through careful choices in compiler, kernels, precision, batching, scheduling, and hardware settings. CarbonForge aims to enable the next generation of AI inference to scale sustainably and company own their intelligence.

Role Description The Infrastructure Engineer role at CarbonForge is a full-time, on-site position based in the Greater Montreal Metropolitan Area. In this role, the engineer will design, implement, and maintain infrastructure to support high-performance AI inference workloads, including servers, networks, and related cloud resources. Day-to-day activities include monitoring system health, optimizing infrastructure for reliability and performance, and collaborating with engineering teams to integrate and scale CarbonForge’s optimized inference containers. The Infrastructure Engineer will also diagnose and resolve infrastructure issues, improve deployment pipelines, and help ensure secure, resilient systems. This position involves working closely with colleagues to continuously refine infrastructure architecture and support the company’s mission of efficient AI at scale.

Qualifications

• Strong infrastructure skills, including experience with server management, virtualization or containerization, and scalable system design.
• System administration skills covering operating systems (Linux preferred), configuration management, and performance monitoring.
• Networking skills, including familiarity with routing, switching, load balancing, and network protocols.
• Network security skills, including implementing security controls, monitoring for threats, and maintaining secure configurations.
• Troubleshooting skills for diagnosing and resolving complex infrastructure, networking, and performance issues.
• Experience with cloud platforms (such as AWS, GCP, or Azure) or hybrid cloud/on-prem environments is beneficial.
• Familiarity with infrastructure-as-code tools (e.g., Terraform, Ansible) and CI/CD pipelines is an asset.
• Bachelor’s degree in Computer Science, Engineering, or a related field, or equivalent practical experience.
• Ability to work collaboratively in a fast-paced startup environment, with clear communication and documentation practices.