Deepspatial - Senior Data Scientist

About the Company

Deepspatial Inc. is an artificial intelligence technology SaaS company at the forefront of geospatial artificial intelligence and geographic information systems. The company specializes in providing robust, AI-powered solutions to businesses by leveraging the power of geospatial data.

Qualifications:

- Undergraduate degree in Computer Science, Statistics, Operations Research, or a related field

- Master's degree in Computer Science, Statistics, Operations Research, or a related field

- PhD (preferred)

Key Skills:

- Passion for Data Quality and Scaling Data Science Work

Data Types & Structures:

- Types of Data, Data Structures, Data Serialization Formats

Data Preprocessing:

- Data Cleaning, Data Transformation, Feature Engineering

Exploratory Data Analysis (EDA):

- Descriptive Analytics, Multivariate Analytics

Data Modeling Techniques:

- Predictive Modeling, Descriptive Modeling, Prescriptive Modeling

Data Visualization:

- Principles, Visualization Tools and Libraries, Types of Charts and Graphs

Programming:

- Expert in at least one programming language for data analysis (e.g., Python, R, Java, MATLAB)

Model Evaluation and Validation:

- Performance Metrics, Handling Overfitting and Underfitting, Confusion Matrix, AUC, ROC, etc.

Spatial Data Analysis with Python:

- Experience with Static and Interactive Maps

Geocoding & Reverse Geocoding:

- Using Free Open Sources

GIS & Remote Sensing Software:

- Exposure to Open-source GIS and Remote Sensing tools (ArcGIS, QGIS, SCP, OTB toolbox)

Machine Learning Algorithms:

- Experience with Supervised and Unsupervised Classification Methods:

- eXtreme Gradient Boosting (XGBoost)

- K-Nearest Neighbour (KNN)

- Nave Bayes (NB)

- Random Forest (RF)

- Clustering

Classification-based Algorithms:

- Training Data Model Accuracy, Kappa Index, Variables Importance, Sensitivity Analysis of Explanatory and Response Data

Hyper-parameter Optimization:

- Procedure and Application

Algorithmic Innovation:

- Ability to innovate custom algorithmic solutions to machine learning problems

Work Environment:

- Proven ability to succeed in both collaborative and independent work environments

Detail-Oriented:

- Excited to learn new skills and tools

Analytical Skills:

- Ability to take an ambiguously defined task and break it down into an insightful analysis

Design & Visualization:

- An eye for design when it comes to dashboards and visualization tools

- Familiarity with Experimentation and Machine Learning Techniques

- Data Analytics Tools on AWS Cloud

- Geospatial Data Dashboards:

- Ability to synthesize and create geospatial data dashboards using modern tools (e.g., Keplr, ESRI, Carto