Data Scientist

Data Scientist

Job Description

Job Description:

As a Data Scientist, you will join a team leveraging petabyte-scale datasets for advanced analytics and model building to enable intelligent, automated equipment and improved decisions by farmers. Our team partners with product managers and data engineers to design, scale, and deliver full stack data science solutions. Join a passionate team making a difference by applying innovative technology to solve some of the world's biggest problems.

You will:

Communicate with impact your findings and methodologies to stakeholders with a variety of backgrounds.
Work with high resolution machine and agronomic data in the development and testing of predictive models.
Develop and deliver production-ready machine learning approaches to yield insights and recommendations from precision agriculture data.
Define, quantify, and analyze Key Performance Indicators that define successful customer outcomes.
Work closely with the Data Engineering teams to ensure data is stored efficiently and can support the required analytics.

Relevant skills include:

Demonstrated competency in developing production-ready models in an Object-Oriented Prog language such as Python.
Demonstrated competency using data-access and processing technologies such as SQL, Spark, and Databricks to query, transform, and analyze large-scale datasets efficiently.
Experience creating clear, actionable visualizations using tools such as Tableau, Kepler.gl, and QGIS (dashboards, interactive maps, and spatial analysis outputs).
Experience with Data Modeling techniques such as Normalization, data quality and coverage assessment, attribute analysis, performance management, etc.
Experience building machine learning models such as Regression, supervised learning, unsupervised learning, probabilistic inference, natural language modeling, etc.
Excellent communication skills. Able to effectively lead meetings, to document work for reproduction, to write persuasively, to communicate proof-of-concepts, and to effectively take notes.
Experience with model validation, measuring model bias, measuring model drift, etc.

What makes candidates stand-out are skills such as:

Experience with Geospatial data search and analysis, geo-indexing techniques, vector and raster data structures.
Experience with remote sensing, GIS tools, and satellite imagery analysis.
Hands-on experience building, using, and deploying computer vision models (object detection + segmentation), including using Segment Anything (SAM) for promptable/automatic segmentation
Hands-on experience building and deploying advanced AI solutions (agentic systems/tool use, RAG with vector databases, foundation model adaptation/fine-tuning, and production-grade AI deployments with evaluation, monitoring, and governance).
Examples of professional work such as publications, patents, a portfolio of relevant project-work, etc.
Experienced with a variety of data structures such as time-series, geo-tagged, text, structured, and unstructured.
Additional experience with other languages such as Java, JavaScript, Scala, etc.
Experience with simulations such as Monte Carlo simulation, Gibbs sampling, etc.
Experience collaborating with stakeholders from disciplines such as Product, Sales, Finance, etc.
Ability to communicate complex analytical insights in a manner which is clearly understandable by nontechnical audiences.

Education: preference for MS or PHD level candidates.

VIVA is an equal opportunity employer. All qualified applicants have an equal opportunity for placement, and all employees have an equal opportunity to develop on the job. This means that VIVA will not discriminate against any employee or qualified applicant on the basis of race, color, religion, sex, sexual orientation, gender identity, national origin, disability or protected veteran status