Senior Software Engineer

• Oct 2023 - Present

Apache Arrow PMC member

• Oct 2022 - Present

Senior Software Engineer

• Apr 2022 - Oct 2023

Open Source Developer

• Apr 2021 - Mar 2022

Senior Consultant

• Jul 2018 - Mar 2021

Created a complex multi-step NLP pipeline in Python for conducting aspect-based sentiment analysis on TripAdvisor reviews. Utilised techniques such as Conditional Random Fields, fuzzy matching, and a pre-trained Word2vec model, improving initial model performance on a small dataset from 40% accuracy to around 90%. Successfully deployed analytics pipeline on AWS. Developed a large scale Shiny app containing advanced visualisations. Responsible for writing PostgreSQL functions to supply data for the application. Co-designed a scaled-up version of the app which is currently being used within the NHS. Delivered a presentation about this work at RStudio Conference in January 2019. Used acquired knowledge to shape internal best practice guidance on R and Shiny in production environments. Show less

Data Scientist

• May 2016 - Jul 2018

Consulted on a number of projects involving developing R packages and Shiny applications, developing in-depth knowledge in these areas, and gaining experience of using a wide selection of R packages. Successfully co-authored “Developing R Packages” course, which is now live on Data Camp, and has very positive course ratings. Created and delivered workshops and training courses on a range of topics, ranging from introductory to advanced R and machine learning. Delivered private training courses and conference workshops internationally, consistently receiving excellent feedback from attendees. Developed an automated static code analysis package and application in R, which has been used to guide part of a large-scale redevelopment drive at the Office for National Statistics. Independently carried out an in-depth needs analysis and scoping exercise, involving use of this software, for a large organisation in the financial services industry which led to agreement of a much larger subsequent SAS to R and Spark conversion project. Developed a Shiny application for a client in the pharmaceutical industry to combine data from multiple sources, automate literature searches, and perform statistical analyses, resulting in enthusiastic adoption by the end users and a later project to further extend its functionality. Show less

Smarter Workforce Specialist

• Jul 2015 - May 2016

Utilised analytical expertise to modify and create dummy datasets, resulting in sellers delivering compelling product demonstrations. Utilised analytical expertise to modify and create dummy datasets, resulting in sellers delivering compelling product demonstrations.

Graduate Teaching Assistant

• Oct 2011 - Jul 2014

In this role, I assisted with weekly workshops for MSc Psychology students around the topic of statistics and research methods. Empowered students to develop their understanding of the topics covered in class, being commended by my students as being “approachable” and “friendly”. This role also involved delivering revision sessions exploring materials from past papers in great detail. During the time I was assisting teaching the course, there was a 100% pass rate. In this role, I assisted with weekly workshops for MSc Psychology students around the topic of statistics and research methods. Empowered students to develop their understanding of the topics covered in class, being commended by my students as being “approachable” and “friendly”. This role also involved delivering revision sessions exploring materials from past papers in great detail. During the time I was assisting teaching the course, there was a 100% pass rate.