Machine Learning Engineer
Project Overview:
We are seeking a highly skilled and versatile Machine Learning and Data Engineer to join our team. This role involves developing sophisticated image-based solutions for plant phenotyping and pulling, stitching, and wrangling data from various sources for advanced analytics. The successful candidate will work on a cross-functional team, collaborating closely with crop scientists, plant pathologists, cloud engineers, and data scientists to enable access to relevant data and deploy machine-learning models and solutions.
Responsibilities:
-
Develop and implement image-based solutions for quantifying various traits and features of plants.
-
Pull data from first and third-party sources, prepare it for analysis by filtering, tagging, joining, parsing, and normalizing datasets.
-
Collaborate with team members to research data sources, design and deploy data loaders, and ensure the availability of data for analytical activities.
-
Provide technical expertise in the design and implementation of data management and architecture solutions.
-
Develop, evolve, and implement concepts of data ops in partnership with cloud and ML engineers.
-
Architect, develop, deliver, and support ML products and solutions, ensuring successful deployment into production.
-
Automate model training, testing, and deployment processes.
-
Design, develop, and maintain scalable data pipelines and ETL processes.
Requirements:
-
Master’s degree or higher in Data Science, Computer Science, Computer Engineering, Electrical Engineering, Robotics, Physics, Mathematics, or related fields.
-
Deep understanding and experience with Image Theory, Deep Learning, Machine Learning, Python Programming, TensorFlow, or PyTorch.
-
Strong experience in designing and implementing large-scale data processing, analysis, and exploration solutions.
-
Proficiency in R, Python, advanced SQL skills, and a good understanding of data management principles.
-
Experience with cloud technologies (Azure or GCP preferred) and deploying CI/CD pipelines.
-
Knowledge of Git, PySpark, Data Bricks, and database management (SQL/PLSQL/Snowflake preferred).
-
Excellent communication skills and the ability to work independently and collaborate across teams.
-
2+ years of industry or academia experience in image processing, computer vision, or related fields.
Work Details:
-
Location: Remote, candidates must work in the PST time zone.
-
Work Hours: 40 hours per week.
-
We sponsor US work visa after 1 year of service
