Data Scientist - Data Infrastructure and Tools Folium Plotly SuperAnnotate Labelbox Voxel51 Python AWS SQL Spark Databricks MongoDB Javascript

NOTE: W2 only. No C2C please.

NOTE: Prefer candidates that can work at the client facility in Urbandale IA. Remote for only the most qualified of candidates.

NOTE: Sponsorship is not available for this role now or in the future. Thank you.

Data Scientist Data Infrastructure & Tools

This role will be working for Aquent Studios as a Data Scientist for one of our top clients teams with a focus on scaling infrastructure to support data science work. This includes labeling & visualization systems/platforms and data processing and transformation. In this role you will join a dynamic team utilizing petabytescale datasets for advanced analytics and model building to develop data tools and infrastructure around labeling & system performance management systems. Your expertise will contribute to enabling intelligent automated equipment and improved decisions for farmers. We are looking for individuals who are passionate about applying innovative technology to solve some of the worlds most substantial problems.

Key Responsibilities:

• Design build and scale tools and infrastructure around data labeling systems (e.g. SuperAnnotate Labelbox Voxel51) including the development of plugins for spatial visualizations over maps.
• Scoping out work and estimating timelines work in an Agile environment and executing on deliverables.
• Define quantify and analyze key performance Indicators to support successful outcomes.
• Collaborate with other data scientists and engineers to build and test solutions.
• Communicate your progress recommendations methodologies and insights with stakeholders from various backgrounds.

Required Skills:

• Demonstrated competency in developing productionready code using Python & AWS infrastructure (e.g. S3 policies etc).
• Proficiency in using dataaccess technologies such as SQL Spark Databricks MongoDB.
• Experience with data storage and management of various types of data (e.g. images rasters parquet timeseries geotagged text and other unstructured data).
• Familiarity with spatial visualization tools (e.g. Folium Plotly) and labeling systems like SuperAnnotate Labelbox Voxel51.
• Experience in developing alerts (e.g. through email automation) dashboards (e.g. Tableau) or other means to monitor system performance and issues.
• Excellent communication skills including the ability to lead meetings document work for reproduction write persuasively communicate proofofconcepts and effectively take notes.
• Capacity to communicate complex analytical insights in a manner understandable by nontechnical audiences.

Additional Preferred Skills:

• Experience developing plugins with other programming languages such JavaScript.
• Knowledge of model validation measuring model bias and measuring model drift.