Dr. Chris Fourie#

I am a medical doctor turned MLOps engineer and health data scientist, trying to use the powers of AI for social good.

I have been working full-time as an MLOps engineer for analysis of continuous and remote monitoring health data at LifeQ. Part-time I provide consulting services for digital health, artificial intelligence (AI) / machine learning (ML) and software engineering.

I have a medical degree (MBBCh) and a master's in computer science from the University of the Witwatersrand (Wits) in South Africa. I carried out master's my research under the supervision of Prof. Benjamin Rosman as a member of the Robotics, Autonomous Intelligence and Learning Lab. Additionally I lecture the health analytics course for the Wits Faculty of Health Sciences.

I co-founded SisonkeBiotik, a grassroots participatory research community making AI/ML for health research in Africa more accessible. I also co-founded Grassroots-Parti, a collective of communities with a focus on helping incubate and provide mutual support for grassroots participatory communities in Africa.

I am motivated by my experience growing up in South Africa, witnessing the devastating effects of perpetuated inequality. During my medical training, I saw first hand the challenges this has created and the impact that resource scarcity can have on the health and wellbeing of individuals. My long term research and career interest intersect at collaboratively developing solutions to address inequality, with consideration for the diverse and complex nature of our societal systems.

Curriculum vitae#


Industry experience#

My experience spans is chiefly as an MLOps engineer which spans software engineering (cloud, backend and DevOps), data engineering and data science. I am very familiar with container based micro-services and pipelines for data (ETL), ML model training and ML model serving.

Platforms / tools / frameworks that I have worked with include

  • Languages: C, Java, TypeScript, Python
  • Cloud
    • AWS: Boto3, Chalice, Batch, SQS, SageMaker, DynamoDB, Lambda
    • Terraform
  • DevOps: Jenkins, Airflow
  • Backend: Postgres DB, SQL, noSQL
  • Data science / ML: SciKit learn, PyTorch, TensorFlow, NumPy, Pandas, Seaborn, Matplotlib, OpenCV, OpenAI Gym, Stable baselines, MLFlow, Weights & biases
  • Docker, Git, Linux

More info on MLOps here

Current commitments#

Independent technical consultant for RetroRabbit

  • Conducting technical interviews for intermediate and senior software engineers

Previous experience#

2020 to 2023 - MLOps Engineer and Health Data Scientist for LifeQ

  • Working on projects related to analysis of health / biometric data from continuous and remote monitoring devices. Generally, machine learning and data pipelines, backend, DevOps and cloud infrastructure for AI / machine learning.
  • Lead on project to investigate using biometric data from wearables for COVID detection, optimised existing approach by decreasing resource requirements while increasing accuracy with multi-modal approach
  • Lead on project for rapid model benchmarking pipeline
  • Worked on project to standardise data science projects as serverless AWS Chalice apps with focus on parallelisation of data pipelines and containerisation

2022 - Technical consultant for Cebisa Health (SA)

  • Strategy consulting for feasibility and implementation of electronic health record platform for schools in Africa

2020 - Technical consultant for Mamba Insights (UK)

  • MLOps software solution implementation for video segmentation and analysis in industrial settings

2020 MLOps Engineer internship at DataProphet DataProphet

  • Projects on ETL and cloud orchestration for ingestion of factory sensor data to ML and data pipelines.

Research experience#

Communities and academic affiliations#

Selected publications#

  • "A Framework for Grassroots Research Collaboration in Machine Learning and Global Health", ML for Global health workshop ICLR 2023 [paper]
  • Chapter Co-Author on "Trauma and Injury" for Essentials of Global Health textbook (British Medical Journal Book Awards, 1st place in Public Health division, published by Elsevier, edited by Parveen Kumar) - [textbook]

Conferences and international academic experience#

  • 2023 - Invited speaker AI for health @ IndabaX Rwanda / ICLR
  • 2023 - Deep Learning Indaba (organising committee)
  • 2023 - DS4Health Workshop @ Deep Learning Indaba (lead organiser)
  • 2023 - Deep Learning IndabaX South Africa (organising committee)
  • 2023 - Invited speaker AI for health @ IndabaX Zimbabwe
  • 2022 - AML Health Workshop @ Deep Learning Indaba (lead organiser)
  • 2022 - Deep Learning IndabaX South Africa (organising committee)
  • 2021 - Deep Learning IndabaX South Africa (organising committee)
  • 2020 - African Institute for Mathematical Sciences (AIMS) African Machine Learning Masters (AMMI) Rwanda, Reinforcement Learning Course (tutor)
  • 2019 - Deep Learning Indaba, Kenyatta University, Nairobi Kenya (presented poster on pan-African ML for health collaboration)
  • 2019 - IBRO-Simons Computational Neuroscience Imbizo / Summer School (participant fully funded)
  • 2014 - South African Medical Association(SAMA) annual conference (student delegation leader)
  • 2013 - IFMSA General Assembly, Tunisia (South African delegation leader)
  • 2013 - Academic Observership at Hospital for Special Surgery, New York

ComSci MSc - Research report#

[full report]

Impact of Noise on Learned Value Functions at Depth in CoAgent Networks for Neural Network Credit Assignment

CoAgent networks (CoANs), networks of reinforcement learning agents, have been shown to be a biologically plausible alternative to backpropagation for solving the neural network structural credit assignment problem [Gupta et al. 2021]. This is accomplished where many agents, each as a neuron in a stochastic neural network, use only their local policy gradient and a global reward. Noise is an important consideration in the learning dynamics of any stochastic neural network [Schoenholz et al. 2017]. We investigate the impact of noise on learnt value functions for baselines and Actor-Critic methods in CoANs at depth. We demonstrate that with additional layers, CoANs using REINFORCE, REINFORCE with a baseline or Actor-Critic methods perform significantly worse. However unbiased variance reduction methods are effective at alleviating this to a moderate extent. For CoANs of increasing depth and width using Actor-Critic methods we show that learned value functions are more sensitive to noise. We show as well that large bootstrapping bias impacts Actor-Critic CoAN methods significantly.

ComSci MSc - Projects#

Machine Learning#
Reinforcement Learning#
Computer Vision#
High Performance Computing#

Algorithm Analysis#

  • Recursive Algorithms - Find max sub-array (Java) - [repository]
  • Search trees - Binary, Red Black and Order statistic (Java) - [repository]


Career direction and opportunity seeking#

There are a variety of career paths I anticipate would bring me joy and prosperity while affording me an opportunity to make a positive impact.

I am interested in being contacted to explore full-time / part-time opportunities in industry / research that are related to any combination of the following:

  • MLOps engineering (Software, backend, DevOps, data and ML engineering)
    • Solution design, implementation and maintenance
    • AI / data pipelines, AI digital infrastructure
    • Responsible AI
  • AI for health
    • Privacy preserving AI for health
    • Multi-modal ML for health
    • AI for adaptive treatment regimes
  • Public and global health
    • AI for data driven health policy development
  • Collective intelligence
    • AI for resource governance
    • Multi-agent modelling
    • AI for multi-agent credit assignment
    • Emergent communication
  • Technical consulting
    • Software and digital
    • Strategy
    • Feasibility
    • Solution design / architecting and implementation
  • Democratic business / co-operatives

Thanks for stopping by (",)

The best way to contact me is via chat or email