Remote, Canada
Events in recent years have made us all too familiar with the havoc natural disasters can wreak and the increasing frequency and intensity with which they occur. Despite record losses, conventional risk modeling methods continue to paint, at best, an incomplete picture of these threats.
ZestyAI uses novel data-gathering and data science methods to produce higher-quality information about the risks to property from catastrophes such as storms and wildfires. While AI alone may not be able to thwart these disasters, it can help us become better prepared for them, and ultimately lead to better outcomes.
As a Senior Data Scientist specializing in deep learning for computer vision, you will play a pivotal role in our Data Science and Machine Learning team. You will be responsible for training, deploying, and optimizing state-of-the-art deep learning models to tackle challenging computer vision problems. You will scale the development of top-tier models by leveraging diverse data sources, generating valuable insights, and maximizing the impact of our products. You thrive in a collaborative, innovative environment that moves fast and are comfortable establishing structures and processes that drive the company’s success.
The Opportunity:
- Explore data sources and develop new PropertyTech and InsurTech models using data science, including machine learning and deep learning.
- Research, design, and implement deep learning algorithms and architectures that extract insights from imagery sources such as aerial imagery and geospatial data.
- Lead the development of high-quality datasets for robust model training and evaluation.
- Collaborate closely with cross-functional teams to understand requirements and translate product, engineering, and business constraints and questions into actionable data science problems.
- Coach and provide feedback to members of the Data Science and Machine Learning team, fostering skill development and knowledge sharing.
What You Bring to the ZestyAI Team:
- At least 5 years of experience applying machine learning techniques to computer vision applications.
- BA/BS/BEng degree in Math, Physics, Computer Science, Engineering, Economics, or other related fields. MS or PhD is a plus.
- Strong understanding of image processing, machine learning, deep learning, and AI principles.
- Extensive hands-on experience designing and implementing deep learning models.
- Experience deploying deep learning models in production environments.
- Proficiency in Python, with experience using deep learning frameworks (e.g., PyTorch, TensorFlow) and related libraries (e.g., OpenCV, Pillow, Matplotlib, Plotly).
- Understanding of data preprocessing and augmentation techniques for large-scale image datasets (bonus if experienced with aerial or satellite imagery).
- Experience working with cloud computing platforms (e.g., Google Cloud Platform, AWS) and containerization/orchestration tools (e.g., Kubernetes, Docker).
- Familiarity with version control systems (e.g., Git) and collaborative development workflows.
- Experience working with BigQuery and SQL.
- Experience using generative AI coding tools such as Claude Code and Cursor.
- Excellent problem-solving skills and ability to work independently or as part of a team in a dynamic environment.
- Strong organizational and management skills, with experience implementing best practices and processes.
- Proven ability to mentor and guide junior team members, fostering a collaborative and supportive environment.
- Strong communication skills.
- Must be legally eligible to work in Canada.
Why ZestyAI:
- Be part of a well-funded, growth-stage start-up.
- Market-competitive compensation and equity incentives, giving you a stake in our future.
- Comprehensive healthcare plan.
- Flexible time off and fully remote work.
- An upbeat and collaborative work culture.
- Professional development opportunities and support for continued learning and growth.
- Company-sponsored outings and offsites.
All of your personal information will be kept confidential according to EEO guidelines.
