Skip to content
View JakobFerschin's full-sized avatar

Block or report JakobFerschin

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 is supported. This note will only be visible to you.
Report abuse

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

Report abuse
JakobFerschin/README.md

Jakob Ferschin

Software Engineer building at the intersection of data systems and business logic. Currently studying Business Informatics at WU Wien and joining the Oesterreichische Entwicklungsbank (OeEB) as a Mid-Office IT Intern this summer.

💻 Engineering

GovTender AI

An enterprise-grade B2B platform for public procurement analysis and predictive winner matching in the EU/DACH region.

  • Features: Deterministic "Non-LLM First" data pipeline, CPV-based historical matching algorithm, and an executive intelligence dashboard.
  • Stack: Next.js, TypeScript, Supabase, Tailwind CSS

M&A Due Diligence Copilot

An LLM-powered platform that automates pre-merger due diligence memos for strategy consulting.

  • Features: Structured JSON outputs via Pydantic, dynamic source-provenance tagging, and automated DOCX memo generation.
  • Stack: Python, Streamlit, Supabase, OpenAI/GLM APIs

ADMET-Engine

A full-stack molecular property prediction system for drug discovery.

  • Features: DMPNN inference predicting 12 toxicity endpoints directly from SMILES inputs in under 500ms per batch.
  • Stack: PyTorch Geometric, FastAPI, React, TypeScript, RDKit

🏢 Experience

  • IT Associate @ BCS Business Consulting Society Vienna
  • Director of DACH Expansion @ Handprint Tech

🛠️ Stack

TypeScript Python Next.js React SQL Supabase FastAPI PyTorch n8n Tailwind CSS

📫 Connect

LinkedIn · jakob_ferschin@protonmail.com

Popular repositories Loading

  1. ma-dd-copilot ma-dd-copilot Public

    AI-powered M&A Due Diligence Memo Generator with mandatory source citations, PDF extraction, and DOCX export. (Architectural showcase for Pydantic/Streamlit/LLM integration).

    Python

  2. Admet-Engine Admet-Engine Public

    Full-stack molecular property prediction system using Directed Message-Passing Neural Networks (DMPNN).

    Python

  3. JakobFerschin JakobFerschin Public

  4. GovTender GovTender Public

    An enterprise-grade B2B platform for deterministic public procurement analysis and predictive winner matching in the EU/DACH region. Built with a non-LLM first architecture, Next.js, and Supabase.

    TypeScript