Data Scientist

The Data Scientist will design and deploy machine learning and deep learning solutions to support early warning systems and humanitarian decision-making within NRC's CLEAR platform. This role involves building predictive models, working with multimodal datasets, and collaborating with AI leads and engineers to ensure scalable and robust AI solutions for humanitarian response.

Responsibilities

• Support the design and implementation of CLEAR’s data architecture.
• Partner with developers and data engineers to design and establish the environment for training and fine-tuning models including data ingestion pipelines, compute and GPU resources, experiment tracking and MLOps tooling.
• Develop machine learning and deep learning models integrating multiple data streams to detect early indicators of humanitarian crises.
• Build computer-vision and remote-sensing models on satellite and aerial imagery for tasks like flood-extent mapping, building detection, displacement-site monitoring, infrastructure damage assessment and land-cover change detection.
• Fuse earth observation outputs with non-imagery signals into unified risk assessment frameworks.
• Contribute to building automated alert systems identifying emerging crises and calibrate prediction algorithms for different crisis types.
• Create ensemble modelling approaches combining traditional statistical methods with advanced AI techniques.
• Fine-tune and adapt foundation models and large language models for humanitarian use cases such as document triage, multilingual report analysis and situation summarisation.
• Explore adapting models to evolving crisis conditions through reinforcement learning systems.
• Implement impact-based forecasting systems translating meteorological, conflict, and economic predictions into humanitarian consequences like displacement volumes, food insecurity levels, and infrastructure damage estimates.
• Build decision trees and recommendation engines guiding field staff through needs assessment processes informed by predictive analytics and historical response data.
• Create automated reporting systems and interactive dashboards for real-time data access by field teams and leadership.
• Perform other tasks assigned by the CLEAR Technical Lead and AI Lead related to CLEAR data.

Requirements

• Advanced degree in Data Science, Statistics, Computer Science, Physics, Engineering, Economics or a related quantitative field.
• Minimum of 5 years of professional experience in applied data science.
• Experience designing, training and fine-tuning deep learning models such as CNNs, recurrent/sequence models and transformers.
• Advanced proficiency in Python and libraries including pandas, NumPy, scikit-learn, TensorFlow, PyTorch and Keras.
• Strong SQL skills for database management and complex query optimization.
• Hands-on experience with supervised and unsupervised learning algorithms including regression, classification, clustering, and time series analysis.
• Proven track record of sourcing, negotiating access to, cleaning and generating data.
• Experience designing and implementing ETL pipelines for multi-source datasets with data cleaning, transformation and quality assurance.
• Ability to create automated reporting systems and dashboards using Tableau, Power BI or similar.
• Experience working with large, messy, real-world datasets.
• Understanding of model deployment and MLOps practices and working with engineers to provision infrastructure.
• Fundamental skills with version control software and collaborative development.
• Fluency in written and spoken English; other languages are an asset.
• Practical experience in low-data or data-scarce settings using transfer learning, few-shot learning, data augmentation and synthetic data generation.
• Experience implementing and fine-tuning large language models (LLMs) for applied tasks.
• Experience with natural language processing for analyzing reports, social media or news data relevant to crisis monitoring.
• Experience using GenAI for automated analysis of large document volumes including theme extraction, sentiment analysis and trend identification.
• Understanding of ensemble methods and explainable AI techniques for transparent decision-making.
• Experience working with earth observation and satellite imagery including optical and radar/SAR sources and geospatial tools like Google Earth Engine, rasterio/GDAL, xarray and geopandas.
• Experience applying computer vision and deep learning to imagery for humanitarian tasks such as flood mapping, damage assessment, settlement detection, infrastructure monitoring and population estimation.
• Experience with multimodal data fusion.

Skills

• Deep Learning Model Design
• Convolutional neural networks
• Recurrent Neural Networks
• Transformer Models
• Python Programming
• Pandas
• NumPy
• Scikit Learn
• TensorFlow
• PyTorch
• Keras
• SQL Query Optimization
• Supervised learning
• Unsupervised learning
• Regression Analysis
• Classification Algorithms
• Clustering Techniques
• Time-Series Analysis
• Data Sourcing and Cleaning
• ETL pipeline design
• Data Transformation
• Data Quality Assurance
• Automated Reporting Systems
• Tableau
• Power BI
• Large Dataset Handling
• Model Deployment
• MLOps principles
• Version Control Systems
• Transfer Learning
• Few-shot Learning
• Data Augmentation
• Synthetic Data Generation
• Large Language Models
• Natural Language Processing
• Generative AI
• Explainable AI Techniques
• Ensemble methods
• Earth Observation data application
• Satellite Imagery
• Google Earth Engine
• rasterio
• GDAL
• Xarray
• Geopandas
• Computer Vision
• Multimodal Data Fusion

Languages

English