Breeding scientist – MT, PR e RS

RS l Rio Grande do Sul, PR l Paraná, MT l Mato Grosso
Efetivo (CLT)
Biólogo
Biotecnologista
Engenheiro Agrônomo

Responsabilidades

• Join a science team that is leading the effort to drive innovative predictive breeding, continuous improvement of data collection and analysis, and pilot algorithmically enhanced decision-making across empresa’s breeding organization.
• Directly contribute to empresa’s core research vision of accelerating genetic gain and developing more resilient, sustainable cropping systems by translating complex biological challenges into AI-powered solutions.
• Conduct crop-agnostic discovery breeding activities to uncover novel native traits and methodologies. Your work will directly translate into a strategic competitive advantage for our soybean pipeline and other key crops.
• Engage directly with a team of plant breeders, domain scientists, data scientists, and software developers assembled to identify business problems, discover new data opportunities, and provide data-driven solutions.
• Manage the deployment of new approaches to breeding decisions directly to breeding teams.
• Identify, acquire, and engineer feature data sets with the potential to address customer needs.
• Apply a spectrum of AI techniques—from machine learning and deep learning to statistical modeling and simulation—to extract insights from complex datasets in agronomic systems.
• Collaborate with scientists from multiple domains in solution/experiment design and analyses.
• Conduct and communicate results of research on data science and AI approaches to improve decisions, add value to services, extend or improve in-house models and algorithms, and contribute to the advancement of these ideas into the marketplace.
• Uphold empresa Core Values at all times.

Requisitos

• QUALIFICAÇÕES MÍNIMAS
  • A PhD in Plant Breeding, Genetics, Data Science, Artificial Intelligence, Statistics, Mathematics, or a related field with demonstrated quantitative genetics knowledge, data science applications or demonstrated equivalent work experience.
  • Understanding of agronomy, crop physiology, and the key challenges facing modern agriculture is a differential.
  • Outstanding problem-solving skills and a proven ability to independently deliver analytic solutions by asking the right questions, identifying necessary data sources, and building and validating predictive models.
  • Demonstrated expertise in applying AI and Machine Learning (ML) to solve complex scientific problems. This includes hands-on experience with deep learning, data mining, statistical methodology, or simulation modeling.
  • Experience with high-throughput phenotyping data (e.g., drone/satellite imagery, sensor data) and integrating it into predictive models.
  • Working knowledge of optimization techniques, especially in the areas of unconstrained optimization, greedy algorithms, dynamic and linear programming, network flows, and genetic algorithms.
  • Experience with complex cross-validation, such as data with unbalanced hierarchical nesting and/or time series components.
  • Expert in scientific computing and high-performance math libraries with Python and/or R.
  • Strong skills in building visualizations of scientific data, including a working knowledge of at least one scientific user interface framework such as Dash/Plotly or RShiny.
  • Proven ability to work in a team setting and to complete complex projects on time and in budget.
  • Superior communication skills, both verbal and written.
• QUALIFICAÇÕES PREFERENCIAIS
  • Familiarity and experience with biological systems, plant breeding, quantitative genetics, and genomics data.
  • A track record of pioneering the use of AI in scientific domains, especially in bringing AI/ML solutions to quantitative biology problems where they haven’t been applied before.
  • A passion for leveraging technology to address global challenges, with a clear understanding of how AI can contribute to agricultural sustainability and food security.
  • Comfort in using cloud-based systems and services, especially AWS.
  • Experience building and sharing documented, reusable software libraries for scientific efforts.