Full stack deep learning in visual information space - from data collection and labelling to deploying and monitoring in production: - Data scraping/cleaning/munging: Python/Pandas, R/tidyverse - Visualization and exploratory analysis: Python, OpenCV, Plotly - DL model training: PyTorch, FastAI - Deployment: GCP, DockerFull stack software development: - frontend: Javascript (React) and Typescript - backend: Flask, FastAPI, Python - databases and datastores: Postgres, Redis - containerization and cloud deployment: Docker, GCP (cloud sql, cloud build, cloud run, cloud functions, Pub/Sub) - application monitoring and dashboards: Metabase, Superset, Jupyter notebooks / PlotlyOther projects: - traffic simulations and network analysis: python and various libraries for graph analysis - map-based applications of traffic violation data: React, Deck.gl, Mapbox - statistical analysis and automatic report generation: python notebooks, statsmodels, plotly, R, ggplot2

Anomaly detection in massive data streams (PySpark, Kafka, Elasticsearch, AWS Redshift)

Mining mobility data at Topia (formerly MOVE Guides)

Cryo-electron microscopy and tomography, protein sample preparation and crystallisation, 2D/3D image processing (FORTRAN, R, Python).

Data analysis and visualization of the global patterns of the ectomycorrhizal diversity. Development of the statistical analysis module for a web based workbench for ecological and taxonomic research (HTML, CSS, Javascript, R).

GUI and feature development, report generation, debugging (PHP, SQL).