Digital Plant Phenotyping & Machine Learning Intern Chesterfield, Missouri, US - Bayer

YOUR TASKS AND RESPONSIBILITIES

In this role, you will implement and optimize advanced deep learning and machine learning approaches to generate actionable insights from imaging and sensor data, supporting data-driven decision making in plant phenotyping and agricultural research.

• Implement and optimize deep learning and machine learning algorithms, leveraging generative models for actionable insights and solutions;
• Evaluate needs, recommend experiments and projects, advocate for novel algorithmic pursuits, and inform strategic decisions;
• Utilize imaging and sensor technologies to collect and analyze phenotypic data, such as plant growth, plant development, and biotic and abiotic responses;
• Communicate results in a timely and organized fashion to project teams and key stakeholders through scientific reports and presentations;
• Solve complex problems autonomously requiring original thinking, creativity, and deductive reasoning, and apply scientific principles to the design and interpretation of scientific experiments;
• Perform multiple experimental protocols under supervision, as needed;
• Prioritize and coordinate work within a matrixed testing environment while maintaining detailed record keeping and required documentation;
• Demonstrate strong commitment to safety and compliance by adhering to safety protocols and best practices.

Bayer seeks an incumbent who possesses the following:

• Enrollment in a master’s or Ph.D. program in Computer Science, Electrical Engineering, or an agricultural science program with a focus on computer vision or machine learning;
• Solid foundation in Python programming and familiarity with deep learning frameworks such as Tensor Flow or PyTorch;
• Experience with model architectures and tools including Res Net, YOLO, R-CNN, Deep Lab, GANs, VAEs, and Transformers;
• Experience with hardware and sensing platforms such as RGB-D cameras, LiDAR sensors, robotics, and other imaging or phenotyping systems.

• Previous experience with cloud platforms for model deployment, including AWS, Google Cloud, or Azure;
• Experience using computer modeling techniques for plant development and image-based plant phenotyping;
• Experience implementing machine learning and statistical models to identify or evaluate biotic and/or abiotic stresses in plants.