Skip to content
View tkimhofer's full-sized avatar
  • Germany

Block or report tkimhofer

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. 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
tkimhofer/README.md

πŸ‘‹ About

I'm a data scientist & engineer with a research background and a hands-on mindset for turning ideas into working software. I design and build robust, production-grade data solutions β€” from early-stage prototypes to fully deployed systems.

My work spans the full stack: cloud data pipelines, ML workflows, REST APIs, and web integrations. Whether for SaaS platforms or internal tools, I focus on performance, transparency, and practical usability.

πŸš€ What I do

  • Rapidly prototype and scale data & ML pipelines (Databricks, GCP, BigQuery)
  • Build and deploy APIs and backend systems for production use (e.g. procurement, manufacturing)
  • Deliver analytics-driven tools for e-commerce (Shopify, headless APIs, custom dashboards)
  • Optimise code and computation with C++, Rcpp/Armadillo, and efficient infra
  • Support end-to-end lifecycle: from idea to global rollout
  • Explore and define new use cases as a freelance contributor

🧠 Previously

  • Senior Data Analyst E-commerce, omos media β€” built Shopify-integrated tools for order quality assurance and demand forecasting
  • Senior Expert, ALDI Data & Analytics β€” led design, prototyping, and rollout of data use cases across international buying and supplier domains (SaaS model)
  • Lecturer & Research Fellow β€” headed data science and ML projects in metabolomics at Imperial College London πŸ‡¬πŸ‡§ and Murdoch University πŸ‡¦πŸ‡Ί

πŸ“¦ On GitHub

Most of what’s public here reflects academic and open development efforts.

Many recent projects are proprietary and are not publicly visible.

🀝 Freelance & Collab

Into smart tools, lean builds, and real-world impact?
Let’s connect.

LinkedIn

Pinned Loading

  1. retrieval-gen retrieval-gen Public

    End-to-end Retrieval Augmented Generation (RAG) workflow for council meeting minutes of Stadtrat Duisburg.

    Python

  2. checkpoint_fragebogen checkpoint_fragebogen Public

    πŸ‡©πŸ‡ͺ πŸ‡¬πŸ‡§ πŸ‡ΉπŸ‡· πŸ‡ΊπŸ‡¦ Multilingual desktop app for anonymous STI testing at Aids Hilfe Duisburg & Kreis Wesel

    TypeScript

  3. metabom8 metabom8 Public

    R library for 1D NMR metabolomics workflows. Features include Bruker NMR data import and preprocessing, statistical modeling (PCA, O-PLS), metabolite identification, and visualization (ggplot2, plo…

    R 3 5

  4. nmr_visualisation nmr_visualisation Public

    Teaching NMR - Interactive 3D Bloch-equation simulation of standard 1D NMR pulse and FID detection

    JavaScript

  5. msbrowser msbrowser Public

    MSBrowser is an R Shiny dashboard for interactive visualization and fine-tuning of peak picking parameters in the xcms R package. It supports LC-MS and GC-MS data for small molecule metabolomics an…

    R 7 2

  6. metaboRAG metaboRAG Public

    MetaboRAG is an AI-driven platform interpreting metabolomics data by combining curated biochemical databases and large language models. Using retrieval-augmented generation, it links metabolite cha…

    2