Skip to content
View davidj-brewster's full-sized avatar
3 followers · 3 following

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: YOLO

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: YOLO

Organizations

@researchgate

Block or report davidj-brewster

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
davidj-brewster/README.md

Hi there 👋

Professional Background

I'm a Principal DevOps Engineer working to connect the world of science at ResearchGate in Berlin. I have expertise in backend software and database development, cloud transformation, infrastructure performance, and automation.

Beyond DevOps, most of my GitHub projects are the results of independent research in Medical AI and neuroimaging over the last few months, focusing on:

  • Brain MRI processing, segmentation, and anomaly detection
  • Custom 2D/3D deep learning models for medical imaging
  • Integration of open-source neuroimaging tools

I'm also researching self-correcting & adaptively meta-prompting (pairs of) LLMs with AI-driven reasoning frameworks which I think will supercede pure model strength in a very short period of time - and generating "arbiter" meta-prompts to evaluate model performance objectively.

Featured Projects

Infrastructure & DevOps

AI & Automation

Medical AI & Neuroimaging

Linkedin

https://www.linkedin.com/in/david-brewster-0067a516/

Pinned Loading

  1. video-to-keyframes Public

    Python library and cli tool to identify and extract key-frames from videos based on motion, quality and differential signals

    Python 2

  2. brainMRI-anomaly-pretrained-model Public

    Early project using some of the image, cv2, numpy, torch libraries with mateuszbuda/brain-segmentation-pytorch pretrained unit model

    Python

  3. video-to-3d-brain Public

    Using Intel's Monoculur Depth Estimation technique Deep Learning implementation over an assortment of frames from a single MRI slice to represent the skull in 3D space

    Python

  4. agentic-e2e-dicom-medical-pipeline Public

    Multi-Agentic adaptive FreeSurfer/FSL Registration, ROI-detection, Segmentation, Clustering, Visualisation and Anomaly detection System for DiCOM and NiFTi images and sequences

    Python 1

  5. e2e-brain-MRI-lesion-segment Public

    DiCOM to NiFTI processing pipeline orchestration, combining multiple planes via ANTs to maximise resolution and suitability for clustering and post-processing

    Shell 1

  6. autoadaptive-multi-ai-metaprompting Public

    Improve model Conversational Quality via dialogue not larger model sizes!

    Python 1