Machine Learning Engineer @ cubicfarms Full Time

OVERVIEW

At CubicFarms we believe in the power of technology to feed a changing world. We actively seek talented people who want to make a difference in the ag-tech space by bringing creative ideas to life and leaving an imprint in a healthier, more sustainable world. If you are enthusiastic about joining a dynamic and innovative company on the leading edge of the ag-tech revolution, we invite you to apply!

ABOUT CUBICFARMS

CubicFarms (TSXV:CUB) is an ag-tech company providing automated growing systems for fresh produce and nutritious livestock feed. CubicFarms offers turnkey, commercial scale, hydroponic, automated controlled environment growing systems that can grow predictably and sustainably for 12 months of the year virtually anywhere on earth. The company has sold and installed systems in Canada and internationally and continues to grow a global pipeline of prospective customers. Visit us at www.cubicfarms.com.

THE ROLE: MACHINE LEARNING ENGINEER

We are seeking a Machine Learning Engineer to join our growing Technology team.  Reporting to the Director of Data Science, you will be a pivotal member of the Technology team building the data tools for our customers and operations teams. We are building a data-driven approach to creating a customer experience by democratizing data in which we are delivering data to our people by building intuitive tools so that our stakeholders and consumers can learn independently. We work closely with our stakeholders to gather all the current business questions, so our data models are relevant. A lot of our data comes directly from our users. Every action a user takes in our product is tracked and analyzed, for the goals of identifying areas that are not working well and determining how we can improve. Working with our team you will be exposed to various facets of scientific data science such computer vision, machine learning, automation, predictive maintenance and more.

We are looking for a Machine Learning Engineer who can deeply comprehend the larger data ecosystem system from model requirements to business needs. You focus on designing tools and capabilities that help the team deploy more models to production. You’re able to link what you’re building to the downstream impact of how it will improve our product. You need a passion for data and complexities of data acquisition from a rapidly evolving system. You will experience a wide range of problem-solving situations requiring extensive use of data collection and analysis. You will have a chance to work with structured and unstructured data. You will work closely with a group of Software Engineers, Engineers, Farmers, and Product Managers to create the data infrastructure and tools necessary to drive our team’s initiatives.

EDUCATION & EXPERIENCE

• 4+ years of relevant work experience in developing, automating ML pipelines, and deploying ML models in production environments.
• Bachelor’s degree in Computer Science or related technical field, or equivalent work experience.

THE IDEAL CANDIDATE WILL POSSESS

• A comprehension of fundamental ML concepts and exposure to ML libraries like TensorFlow, Pytorch, and Scikit-learn.
• Advanced Spark or Pyspark skills.
• Intermediate Python and SQL skills.
• Experience optimizing infrastructure usage for performance, reliability, and cost.
• Knowledge of relevant software design patterns and system architecture.
• Experience working with cloud technologies and frameworks and environments such as Airflow and Docker.
• Knowledge of data processing pipelines and data science concepts.
• Experience processing, filtering, and presenting large quantities of data.
• Experience with statistical analysis, data modeling using structured and unstructured data.
• Familiarity managing data science code via Git and DevOps environments.
• Excellent written and verbal communication skills. Strong ability to interact, communicate, present, and influence within multiple levels of the organization.
• Previous experience in image processing is considered an asset.
• Knowledge of Azure services and IoT is considered an asset.

WHAT WILL YOU DO

• Design and implement ML models that scale to thousands of machines.
• Package tests, build containers and deploy artifacts in CI/CD pipelines.
• Work with our Azure services such as storage Gen2, Synapse serverless, Azure functions, Azure Machine Learning, and Databricks.
• Create the interfaces, infrastructure, and clusters to process data efficiently.
• Work with data science team to improve our ML platform: logging, monitoring, scalability, model retraining, automated testing, environment isolation, and model health monitoring.
• Build pipelines that process big data.
• Collaborate across teams to evaluate the highest-impact opportunities.
• Contribute to develop data strategies from IoT and other devices.
• Implement and develop tools to monitor and analyze data accuracy and performance.
• Formulate and build data processing pipelines to fuel data-driven research (e.g., statistics, machine learning, & data mining)
• Research, develop, and implement artificial intelligence into a variety of data ingestion sources.
• Working with PM, UX teams and full-stack engineering teams to build data-powered features in our cloud dashboard.
• Capture and share industry best practices amongst the company.

EQUAL OPPORTUNITY EMPLOYER

CubicFarms is an equal opportunity employer is committed to building a team that represents a variety of backgrounds, perspectives, and skills. We encourage applications from all qualified and enthusiastic candidates. CubicFarms is a growing organization in an emerging industry that will provide the right candidate with significant potential for advancement in the ag-tech space.