Machine Learning Ops Engineer

HRB; Canada; Remote; CAD 80,000 - 120,000; Full time

Job summary

Join an innovative startup as a Machine Learning Operations Engineer, contributing to groundbreaking wildfire prevention technology. You will work collaboratively with experts to deploy and automate machine learning models, optimizing processes to address environmental challenges while ensuring model reliability and performance.

Qualifications

• 5+ years of experience in machine learning, focused on environmental or geospatial applications.
• Expertise in machine learning frameworks (TensorFlow, PyTorch, JAX).
• Familiarity with distributed computing frameworks and cloud platforms.

Responsibilities

• Transition experimental ML models into production-ready services.
• Work with large-scale data sources to support model development.
• Implement monitoring solutions to track model performance.

Skills

Machine Learning

Geospatial Applications

Computer Vision

Data Analysis

Collaboration

Tools

TensorFlow

PyTorch

JAX

Job description

Machine Learning Operations Engineer

Remote - Canada

Your opportunity

Founded in 2024 our client is an early-stage startup with a pioneering approach to wildfire prevention, leveraging novel, predictive models to prevent catastrophic wildfires ignited by lightning over (and near) high-risk areas.

Lightning strikes account for 60% of wildfires in Canada, resulting in 93% of the burned area and emissions—their technology focuses on reducing wildfire occurrences and emissions by suppressing lightning strikes before they ignite these fires.

Their work combines cutting-edge geospatial data analysis, machine learning, and computer vision to create a first-of-its-kind solution that anticipates and prevents lightning-induced wildfires at their source. This is a rare opportunity to build entirely novel capability and to contribute to a critical area of research that’s largely uncharted.

As a Machine Learning Operations (ML Ops) Engineer, you will play a critical role in bridging the gap between research and scalable production systems.

Amongst a range of responsibilities, you can expect:

• Collaboration & Innovation: Partner closely with data scientists, machine learning engineers, and domain experts to integrate models into an IRL ecosystem

• Model deployment: Transition experimental machine learning models into robust, production-ready services with containerization tools and orchestration platforms to ensure reliable model serving in a dynamic environment

• Pipeline automation: Work with large-scale, diverse data sources (real-time weather data, satellite imagery, and historical fire records) to support model development and ensure data consistency

• Monitoring & maintenance: Implement comprehensive monitoring solutions to track model performance, detect data drift, and trigger retraining as needed

• Infrastructure management: Optimize resource allocation to balance performance with cost efficiency

• Collaboration & cross-functional work: Partner with data scientists, software engineers, and environmental scientists to integrate models and translate findings into actionable strategies

What we’re looking for

• 5+ YOE in ML, ideally with a focus on environmental or geospatial applications and experience deploying models in production

• Motivation to apply machine learning for environmental impact, with a passion for solving real-world challenges in a fast-paced, early-stage startup environment

• Expertise in machine learning frameworks like TensorFlow, PyTorch, or JAX

• Experience with time-series analysis and computer vision techniques, particularly for satellite imagery, object detection, and segmentation

• Experience in model architecture design, hyperparameter tuning, and deployment

• Familiarity with distributed computing frameworks, cloud platforms and real-time model deployment

It’s a bonus if

• You have startup/founding experience