Principal ML System Engineer

This is a fully remote position, open to applicants in Canada.

📋 Description

• Act as the product owner for GenAI functionalities within PointClickCare.

• Collaborate with engineering teams to discover, develop, and support generative AI solutions.

• Design, create, and sustain the core infrastructure for GenAI products, which includes model gateways, prompt/versioning stores, vector databases, and LLM evaluation tools.

• Establish secure access controls and authentication methods in components of the AI platform.

• Create and oversee observability, monitoring, and logging for GenAI workloads and infrastructure.

• Connect GenAI infrastructure with agent frameworks and downstream applications.

• Enhance infrastructure for scalability, high availability, and cost-effectiveness in production workloads.

⛳️ Requirements

• Substantial experience in building and maintaining AI platform infrastructure.

• Proficiency with Kubernetes and container security.

• Strong expertise in observability and monitoring frameworks centered on real-time performance.

• Experience with OpenTelemetry and NLPFlow.

• Familiarity with vector databases, prompt/versioning stores, and AI IDEs.

• Knowledge of vLLM, SGLang, or similar frameworks for hosting LLM inference workloads.

• Experience with CI/CD pipelines and automation for deploying AI models and managing platform operations.

• In-depth understanding of authentication and authorization frameworks integrated within AI platforms.

🏝️ Benefits

• Bonus

• Benefits

• Total rewards package