Dr. Chris Fourie#

🧬 Medical + AI/ML/ComSci Background & Current Work 🤖

  • Medical doctor turned MLOps engineer and health data scientist, trying to use the powers of AI for social good.
  • I work full-time as a data / MLOps engineer for the South African Western Cape Provincial Health Data Centre, building digital infrastructure for large scale privacy preserving federated analysis of observational health data.
  • Part-time I provide consulting services for digital health, artificial intelligence (AI) / machine learning (ML) and software engineering.

⚙️ Technical Expertise

  • My experience is primarily as an MLOps engineer for research which spans software engineering (cloud, backend, and DevOps), data engineering and data science.
  • I am very familiar with container based microservices and pipelines for data (ETL), ML model training and ML model serving as well as developing tooling to enable and accelerate computational research in health and biological domains.

🎓 Education & Research

  • My medical degree (MBBCh) and master's in computer science (MSc ComSci) were carried out at the University of the Witwatersrand (Wits) in Johannesburg, South Africa.
  • I completed my master's research under the supervision of Prof. Benjamin Rosman as a member of the Robotics, Autonomous Intelligence and Learning (RAIL) Lab.
  • My topic was at the intersection of NeuroAI and multi-agent reinforcement learning (RL), exploring biologically plausible alternatives to backpropagation, in particular how networks of RL agents (CoAgent networks) could be used as nodes/neurons in a neural network.

🌍 Community Leadership

  • In 2020, I co-founded SisonkeBiotik, a grassroots participatory research community making AI/ML for health research in Africa more accessible.
  • Subsequently, I 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 participate as a technical advisor on the steering committee for the Data Science Without Boarders project, a 3-year iniative to develop capacity for federated health data analyses across institutions in Cameroon, Ethopia and Senegal.
  • I am a co-founder for the AfriMedQA project that has created a novel benchmark dataset and rigorous evaluatation of 20+ LLMs for African healthcare data, spanning 32 clinical specialties, contributed by 1k+ African clinicians across 15 countries.

💡 Motivation & Vision

  • I am motivated by my experience growing up in South Africa, witnessing the devastating effects of perpetuated inequity.
  • During my medical training, I saw first hand the challenges this has created - the severe impact that resource scarcity and the legacy of colonialism can have on the health and wellbeing of individuals and their communities.
  • My long term career interests intersect at collaboratively developing industry solutions and forwarding academic efforts to address inequity, with close consideration for the diverse and complex nature of our societal systems.

Resume#

     

Industry experience#

Current commitments#

Full-time#

From 2023 - Data / MLOps engineer for the South African Western Cape Provincial Health Data Centre

  • Building digital infrastructure for large scale privacy preserving federated analysis of observational health data
  • Co-principal investigator for federated analysis with Brazilian national research group CIDACS on TB and syphilis in pregnancy
  • Project lead to establish secure data environments / trusted research environments for research data accessibility, developing tooling for de-identified and synthetic data
  • Project lead for CI/CD pipeline development and Python dependency management in Databricks
  • Development and maintenance of data pipelines for data ingestion and processing from both provincial public health facilities and national public health data repositories

Part-time#

From 2024 - Technical advisor on steering committee for Data Science Without Boarders project

  • Providing strategic direction and feedback on technical design of systems for federated health data analyses and federated machine learning

Previous experience#

Full-time#

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

  • 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

2020 - MLOps Engineer internship at DataProphet DataProphet (ZA)

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

Part-time#

2024 - Technical consultant for FruitPunch AI (Netherlands)

  • Developing experimentation and data pipelines for LLM based inference on genomics data using MPEG-G compression

2024 - Technical strategy consultant for MotherDAO Labs (USA)

  • Developing AI strategy and conducting feasibility analyses for delivering high quality community feedback data for AI alignment customers with a focus on preference and reward modelling

2023 - Independent technical consultant for RetroRabbit (ZA)

  • Conducting technical interviews for intermediate and senior software engineers

2022 - Technical strategy consultant for Cebisa Health (ZA)

  • 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

Platforms / tools / frameworks#

  • Languages: Python, C, Java, TypeScript
  • Cloud
    • AWS: Boto3, Chalice, Batch, SQS, SageMaker, Lambda
    • Terraform
  • DevOps: Jenkins, Airflow, Azure DevOps
  • Backend: SQL (Postgres, SQL Server), noSQL (DynamoDB)
  • Data engineering: Databricks, PySpark, Pandas
  • Data science / ML:
    • Neural Networks: PyTorch, TensorFlow
    • Scientific computing: SciKit learn, NumPy
    • Experimentation: MLFlow, Weights & biases
    • Data visualisation: Seaborn, Matplotlib
    • Computer vision: OpenCV
    • Reinforcement learning: OpenAI Gym, Stable baselines
  • Docker, Git, Linux

More info on MLOps here

Academic experience#

Selected publications#

  • 2024 - "AfriMed-QA: A Pan-African, Multi-Specialty, Medical Question-Answering Benchmark Dataset" AAAI (GenAI4Health) [paper]
  • 2024 - "AfriBiobank: Empowering Africa’s Medical Imaging Research and Practice Through Data Sharing and Governance (MICCAI) [paper]
  • 2023 - "A Framework for Grassroots Research Collaboration in Machine Learning and Global Health", ICLR 2023 (ML for Global Health) [paper]
  • 2018 - 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]

Education#

Communities and academic affiliations#

From 2020 - SisokeBiotik (co-founder) [community site], [YouTube], [LinkedIn], [Twitter]

  • Led efforts to found community, developed initial structures, policies and practices
  • Lead for initial projects, events and fundraising efforts
  • Advising leadership team
  • Developing and maintaining strategic relationships

From 2022 - Grassroots Parti (co-founder) [community site]

  • Leading efforts to develop structures, policies and practices
  • Developing and maintaining strategic relationships

2019-2023 - RAIL Lab (member) - [blog], [members]

2023 - Deep Learning Indaba (community organizer) - [community site]

2021-2023 - IndabaX South Africa (community organizer) - [community site]

2019 - Computational Neuroscience Imbizo (alumni) - [summer school]

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]

Robotics#

Conferences and talks#

  • 2024 - Invited speaker for Africa Health Exhibition ("3IR b4 4IR: Data Accessibility to Enable African Data Science, ML and AI for Health" [slides])
  • 2023 - Invited speaker AI for health @ ICLR / IndabaX Rwanda ("AI 4 Health in Production" [slides])
  • 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 - African Machine Learning 4 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)

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

References#

Prof. Andrew Boulle
Technical Director at the
Western Cape Government Provincial Health Data Centre
Public Health Specialist
andrew.boulle@westerncape.gov.za
Citations

George Cooper
Team Lead at LifeQ
MLOps Engineer and Systems Biologist
+27829222334

Prof. Benjamin Rosman
RAIL Lab Director
University of the Witwatersrand
Email: Benjamin.Rosman1@wits.ac.za
Website: https://www.benjaminrosman.com
Citations

Thanks for stopping by (",)

The best way to contact me is via chat or email