Senior ML Platform Engineer – GenAI & MLOps

Jaide Health; Toronto; Hybrid; CAD 140,000 - 190,000; Full time

Benefits offered by this job

Health benefits

Life insurance

Employer savings match

20 vacation days

Wellness days

Unlimited sick days

90 days away program

Job summary

Wealthsimple, Canada’s leading financial innovator, is hiring a Senior MLOps/ML Platform Engineer for the ML Infrastructure & Platform team in Toronto. You will own end-to-end LLM inference platforms, bridging traditional MLOps with GenAI stack needs, including vLLM, GPU cluster management, and model routing.

You'll design scalable, self-serve tooling, optimize cost and performance, and collaborate with data science and product teams to deliver enterprise-grade ML systems across the organization.

Qualifications

• 7+ years of software engineering experience in ML Infrastructure, MLOps, ML Tooling, or Data Platform engineering.

Responsibilities

• Bridge traditional MLOps with GenAI stack requirements (vLLM, GPU cluster management, intelligent model routing).
• Own end-to-end technical direction for operating enterprise-grade LLM systems company-wide.
• Design low-latency model routing and GPU orchestration frameworks.
• Develop automated Evals and observability to validate model quality and latency.
• Collaborate with product engineering and data science teams to build framework-agnostic tooling.
• Drive cost and performance optimization across self-hosted and managed inference.

Skills

MLOps experience

Python

Kubernetes

Terraform

AWS

LLM serving

Architectural leadership

Tools

Kubeflow

MLflow

Ray

Triton

SageMaker

LiteLLM

AWS Bedrock

Job description

Wealthsimple, Canada’s leading financial innovator, is hiring a Senior MLOps/ML Platform Engineer for the ML Infrastructure & Platform team in Toronto. You will own end-to-end LLM inference platforms, bridging traditional MLOps with GenAI stack needs, including vLLM, GPU cluster management, and model routing.

You'll design scalable, self-serve tooling, optimize cost and performance, and collaborate with data science and product teams to deliver enterprise-grade ML systems across the organization.