Senior ML Platform Engineer: GenAI & LLM Infra

Wealthsimple Technologies; Toronto; Hybrid; CAD 140,000 - 190,000; Full time

Benefits offered by this job

Health benefits

Pension/Employer match

Vacation & wellness days

90 days away program

ERGs

Job summary

Wealthsimple Technologies in Toronto is seeking an experienced MLOps or ML Platform Engineer to help evolve our AI footprint. You will join the Machine Learning Infrastructure & Platform team, building scalable systems for hosting open-source LLMs and optimizing inference and GPU management.

You will own end-to-end technical direction, bridging traditional MLOps with GenAI stack needs, including model routing, vLLM, Kubernetes clusters, and observability tooling.

Qualifications

• 7+ years of software engineering experience in ML Infrastructure, MLOps, ML Tooling, or Data Platform engineering.
• Deep experience in MLOps/ML Platform practices (self-serve ML platforms, model registry workflows, experiment tracking, or production serving infrastructure).
• Strong platform fundamentals: Python, Kubernetes, Terraform, and AWS.
• Strong appetite to specialize in LLM serving: vLLM, model routing, prompt engineering tooling, vector databases, GPU memory optimization, or LLM evaluation frameworks.
• Backend performance & observability focus: highly available, observable microservices (FastAPI) handling real-time, low-latency requests.
• End-to-end technical ownership: lead roadmaps and multi-functional projects with autonomy.

Responsibilities

• Turn MLOps expertise to GenAI: transition ML lifecycle to LLM inference engines and GPU orchestration.
• Build model-routing architecture for low-latency routing across clouds and open-source models.
• Provision & scale GPU infrastructure on Kubernetes using vLLM, Ray, and Triton.
• Develop evaluation & benchmarking tooling to validate model quality, latency, and drift.
• Empower self-serve ML across Wealthsimple with framework-agnostic tooling.
• Drive cost & performance optimization for inference across self-hosted and managed environments.

Skills

MLOps experience

Python

Kubernetes

Terraform

AWS

Platform ownership

Model orchestration

Tools

Kubeflow

MLflow

Ray

Triton

SageMaker

vLLM

LiteLLM

AWS Bedrock

FastAPI

Job description

Wealthsimple Technologies in Toronto is seeking an experienced MLOps or ML Platform Engineer to help evolve our AI footprint. You will join the Machine Learning Infrastructure & Platform team, building scalable systems for hosting open-source LLMs and optimizing inference and GPU management.

You will own end-to-end technical direction, bridging traditional MLOps with GenAI stack needs, including model routing, vLLM, Kubernetes clusters, and observability tooling.