Staff Engineer - AI/Inference /Gateway (AI)

Location: Vancouver, Canada; hybrid with at least 3 days onsite per week

Salary: CAD $171,000–$257,000 annually

Company

hirify.global develops the hirify.global Cloud Platform for AI, enabling organizations to build, fine-tune, and run Generative AI, LLM, and Agentic AI applications across on-premises data centers, edge locations, and public clouds.

What you will do

• Architect and develop horizontally scalable, containerized, fault-tolerant services on Kubernetes for enterprise AI and LLM workloads.
• Build and operate low-latency, high-throughput inference and platform services for Generative AI and Agentic AI applications.
• Design distributed systems across compute, storage, networking, virtualization, and other low-level infrastructure layers.
• Develop multi-tenant services for on-premises, hybrid, and cloud-based AI deployments.
• Implement observability, CI/CD, deployment automation, reliability improvements, and production troubleshooting.
• Collaborate with product management, AI, and software engineering teams while contributing across architecture, development, testing, deployment, and operations.

Requirements

• 8+ years of experience developing maintainable, resilient software products in a product development organization.
• Strong fundamentals in data structures, algorithms, operating systems, networking, distributed systems, and datacenter architecture.
• Hands-on experience with Docker, Kubernetes, cloud-native architectures, and multi-tenant services.
• Production backend development experience with Go, Python, C++, or Rust, including high-performance and performance-sensitive systems.
• Experience with CI/CD, release automation, distributed data stores, observability platforms, and deployments across on-premises, cloud, and hybrid environments.
• Knowledge of LLM serving concepts including request routing, rate limiting, token streaming, scheduling, load balancing, quota management, and usage budgeting; a master’s degree in Computer Science or equivalent practical experience.

Nice to have

• Experience with PyTorch, TensorFlow, GPU acceleration, vLLM, DeepSpeed, Hugging Face TGI, or Triton.
• Experience with Retrieval-Augmented Generation, vector databases, AI orchestration frameworks, production LLM APIs, or agentic systems.
• Open-source contributions or experience working in large distributed codebases.

Culture & Benefits

• Hybrid work arrangement with at least 3 onsite days per week in Vancouver and other applicable workplace locations.
• RRSP with dollar-for-dollar matching of up to 7% of base salary.
• Mental health coverage and paramedical benefits.
• Fully paid maternity and parental leave, plus bereavement leave.
• RSUs and an Employee Stock Purchase Plan with a 15% discount.
• Collaboration with a globally distributed enterprise AI team.