LEAD DATA SCIENTIST (COMPUTER VISION)
Join our award-winning team of data scientists, software developers and support engineers who are tackling the biggest problems in our global food systems and are pioneering disruptive innovations using GenAI, computer vision and machine learning. As a Lead Data Scientist (Computer Vision), you'll have primary responsibility for driving our AI strategy, mentoring junior employees and managing a portfolio of computer vision, machine learning and generative AI projects.
About You
You are looking for career growth and want to pioneer new technologies that will have a positive impact on the world. You love fast-paced environments, collaboration, are self-motivated and think outside the box.
About the Opportunity
ThisFish Inc. has developed Tally software for seafood factories that digitizes their production, quality control and traceability data in real-time on the factory floor using tablets and IoT devices. We have developed AI-enabled apps -- called TallyBots -- whose machine learning algorithms are trained on the datasets to improve process control and predict production and quality outcomes in factories. We’re also using computer vision cameras to capture images that we’ll add to our data sets. We want to mine the data for valuable insights that could solve practical day-to-day challenges in seafood processing, quality inspection, food safety and supply chain traceability. As our in-house Lead Data Scientist, you’ll be helping to pioneer the adoption of AI in the seafood sector.
Roles and Responsibilities
Lead, develop and deploy computer vision projects from start to finish
- Develop data collection, annotation and pre-processing methodologies for projects
- Test modern computer vision algorithms such as YOLO or CNN to solve classification, object detection, or other image processing problems
- Deploy models into production systems for real-time processing in partnership with customers
- Define evaluation frameworks and metrics aligned with real-world performance requirements
- Continuously iterate on model architectures and training strategies based on feedback
In collaboration with domain experts, analyze factory datasets for insights to inform the development of AI-enabled solutions to solve practical problems
- Analyze data using exploratory mathematic and statistical techniques and tools such as R or Python and key data science libraries such as numpy, scipy, pandas, pymc3, scikit-learn, matplotlib, keras and pytorch in python or the tidyverse libraries in R.
- Process, cleanse, and verify the integrity of data used for analysis
- Provide insights into improving our data collection methodology
- Present results of analyses with visualizations and clear explanations to domain experts and other interested parties
- Write SQL queries and Python scripts to process data and enable machine learning
Pioneer the use of generative AI agents across both internal and external use cases
- Work with other teams and departments to optimize workflows and tasks by building AI agents using Gemini and other LLMs
- Build and integrate agents into our customer facing application to solve customer problems
- Ensure generative AI is part of the strategy for the growth and optimization of the data science department
Design and build cloud infrastructure that enables the training of machine learning models over millions of historical data points
- Develop infrastructure on Google Cloud Platform to store large datasets for training machine learning algorithms
- Build edge computing solutions for real-time computer vision hardware integrations
- Optimize infrastructure with consideration for pricing efficiency
- Ensure our ETL is reliable, scalable and meets the needs of the business
Manage and mentor the data science team, taking care of administrative tasks and building a culture of performance
- Design and implement a standardized installation and rollout procedure to quickly get new customers onboard with AI applications
- Keep our task tracking board completely up to date, and provide bi weekly updates to senior management on project progress
- Develop, manage and update department OKRs
- Manage relationships with external contractors, including assessing the need for hiring them, reviewing proposals, hours management and project reporting
- Mentor and manage any junior employees in the data science department, including weekly check ins, task management, performance improvements and career progression
Work remotely in a distributed, multicultural team contributing to company strategy, culture and product roadmap.
- Proactive communication to facilitate strong team collaboration across time zones.
- Contribute thoughtfully to team meetings and strategy sessions.
- Excellent verbal and written communication in English.
SALARY & BENEFITS
- Salary: $110,00 CAD to $130,000 CAD depending on experience
- Competitive Benefits Package: We offer employee stock options, 3-weeks vacation and extended medical benefits.
- Flexible Work Environment. We offer the opportunity to work from home with flexible hours. If you are self-motivated and goal oriented, then you’ll love the autonomy of our work culture.
- Learning and Mentorship: Self-improvement, mentorship and career growth are core to our values. We are a growing company and you’ll be able to grow your career with us.
REQUIRED SKILLS & QUALIFICATIONS
Required Skills and Qualifications
- Bachelor’s or Master’s degree or PhD in Data Science, Computer Science, Electrical Engineering, or a related field
- 6+ years of experience in applied machine learning, with a strong focus on computer vision use cases in production environments.
- Expert-level proficiency in Python and deep learning frameworks (PyTorch, TensorFlow,), along with strong experience in NumPy, pandas, and scikit-learn.
- Deep understanding of computer vision techniques including object detection, classification, segmentation, and image processing.
- Proven experience designing, training, evaluating, and deploying end-to-end vision pipelines.
- Strong experience working with large-scale datasets, data preprocessing, and performance optimization.
- Proficiency in SQL and working with structured/unstructured data pipelines.
- Experience with MLOps practices, including model versioning, monitoring, and automated retraining workflows.
- Strong leadership skills with experience mentoring junior data scientists and leading cross-functional projects.
- Excellent communication skills with the ability to translate complex technical concepts into business impact.
- Ability to drive projects independently while collaborating effectively in a remote, cross-functional environment.
Nice-to-Have
- Hands-on experience with YOLO-based architectures, OpenCV, and DepthAI/Luxonis deployment pipelines.
- Experience deploying models on edge devices and optimizing for latency, throughput, and resource constraints.
- Familiarity with cloud platforms such as GCP, AWS, or Azure, including ML services and infrastructure.
- Experience in industrial AI applications such as manufacturing, quality inspection, or food processing.
- Exposure to real-time video analytics and streaming pipelines.
- Interest in sustainable technologies and AI-driven operational efficiency.
- Experience working with global teams; fluency in Spanish or Japanese is a plus.
OUR TEAM
We are a globally distributed, multicultural team originally from nine different countries (and counting!). We believe a diversity of cultures and experiences makes us stronger and generates more inclusive and lasting solutions. We promote employment equity and welcome all candidates regardless of culture, race, religion, age, gender identity, sexual orientation, economic class, physical ability or other status. Join our team to explore the world.
What to Expect
Only candidates selected for an interview will be contacted. Here’s what to expect in our hiring process:
- Application
- 30-minute introductory interview
- Testing (1 to 8 hours depending on role)
- 2 – 3 follow-up interviews with team members and senior managers
- References
- Employment offer