Sam Watts

Continuum Industries

AI Engineer • May 2024 — Present

I'm working with genetic algorithms and machine learning to create tools that enhance the design of large-scale linear infrastructure projects - most noteably electricity transmission lines, whose fast development is crucial for the transition to renewable energy.

University of Edinburgh

Research Fellow • Aug 2023 — Mar 2024

I worked with a novel retinal image dataset to develop deep learning models for the early detection of Age-related Macular Degeneration, Glaucoma and other retinal diseases.

• Implemented semantic segmentation and classification models in Pytorch
• Worked with retinal imaging foundation models using ViT architectures

Too Good To Go

Machine Learning Engineer • Oct 2021 — Mar 2023

I worked on building a product recommendation system from the ground up. My work spanned a range of ML areas, from EDA and model development, to CI/CD and productionising model workflows.

• Designed and implemented a recommender model that increased user purchase conversion by 0.6% pp versus a baseline in A/B tests
• Led the adoption of Metaflow as our ML Workflow tool, significantly speeding up development
• Experimented with new modelling approaches inspired by RecSys 2022

John Lewis Partnership

Lead Data Scientist, Product Recommendations • Mar 2021 — Oct 2021

Led a team of 4 in the design and execution of data science and data engineering work, focusing on development of existing and new recommendations models - whilst still writing production code. Achievements:

• Implemented hyperparameter tuning using sklearn pipelines across all in-house models - boosting recommendation performance in A/B tests
• Iterated on a sequence learning (Prod2Vec) model built on web browsing data in Tensorflow by exposing extra hyperparameters

Data Scientist, Product Recommendations • Aug 2020 — Mar 2021

Responsible for developing in-house recommendation algorithms and ensured they delivered good results in production. Achievements:

• Productionised a previously tested model on GCP, using AI Platform for training and serving
• Drove implementation of a solution for more granular analysis of A/B tests using Airflow and Bigquery
• Organised a regular journal club session, where we discussed recent publications and used them to inform our product roadmap

Data Scientist • Apr 2018 — Aug 2020

Worked on a variety of different projects as one of the first members of a new Data Science team, and gained exposure to a number of different business areas and modelling techniques, including:

• Product demand forecasting
• Online order forecasting
• Supply chain optimisation using vehicle routing models
• Warehouse process simulation and optimisation
• Evaluation of experiments using counterfactual methods

Kubrick Group

Data Scientist • Jan 2018 — Apr 2018

Kubrick provided 4 months of core training in data problem solving along with the key technologies needed to succeed as a data scientist:

• Core Python - data structures, IO, OOP paradigms
• Python libraries for data science & machine learning - sklearn, pandas, numpy
• Advanced SQL
• Git

This training culminated in a group project, in which my contribution was to use the Twitter API to perform an analysis of public perception of different brands based on exemplar accounts. This methodology was adapted from - Culotta, A. and Cutler, J., 2016. Mining brand perceptions from twitter social networks

University College London (UCL)

Natural Sciences, BSc - Organic Chemistry and Neuroscience • 2013 — 2017

DataKind

DataDive Volunteer & Data Ambassador • 2021 - Present

I have volunteered on multiple DataDives - which help charities extract value from their data using data science techniques. I also helped to organise several of these events as a Data Ambassador - by framing key analytical questions, cleaning and documenting data, and liaising with charity representatives to enable volunteers to develop good solutions.

Saturdays.AI Copenhagen

Volunteer Mentor • 2022

Helped teach data science & machine learning foundations to a group of beginners. I taught two sessions, on Exploratory Data Analysis and Clustering.

• Python

• ML libraries - sklearn, tensorflow, pytorch

• SQL - Redshift, Bigquery, MSSQL, Teradata, dbt

• Cloud Platforms - AWS & Google Cloud

• Git

• Docker

• CI/CD - Gitlab, Jenkins, Github Actions

• ML Workflows - Metaflow & AWS Sagemaker

• Terraform

• Airflow

• Technical Blog