Philipp Blandfort, Developer in Berlin, Germany
Philipp is available for hire
Hire Philipp

Philipp Blandfort

Verified Expert  in Engineering

Artificial Intelligence (AI) Developer

Location
Berlin, Germany
Toptal Member Since
October 23, 2019

Philipp completed a PhD in Artificial Intelligence and can look back to 4 years of research experience plus two years of freelancing. His work included text analysis, information extraction from text and images, user behavior analysis, and the creation of datasets. He is performant in interdisciplinary teams and is enthusiastic about building AI systems that help us overcome real-world issues and move in new directions.

Availability

Part-time

Preferred Environment

PyTorch, Docker, Git, Python, Linux

The most amazing...

...software I've developed is a Python-based toolkit that uses NLP to monitor trends in computer science research from publication metadata.

Work Experience

Data Scientist

2019 - PRESENT
Freelance
  • Developed a software package to extract information from scanned documents.
  • Helped to bring code to production by debugging and optimizing performance.
  • Developed a web application to analyze research trends in computer science.
  • Designed and implemented two machine learning pipelines in the bioinformatics domain (NLP and knowledge graph).
Technologies: Scikit-learn, Artificial Intelligence (AI), Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), Docker, Machine Learning, Git, Python, Amazon Web Services (AWS), Algorithms

Visiting Scholar

2016 - 2017
Columbia University
  • Developed an annotation system to annotate social media data.
  • Extracted various concepts from tweets with images, using computer vision and natural language processing.
  • Discussed with researchers from various backgrounds and coordinated the team.
Technologies: Artificial Intelligence (AI), Computer Vision, Annotations, Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), PHP, PostgreSQL

Student Assistant

2013 - 2015
digipen technologies GmbH
  • Developed an algorithm in Java for interpolating and rendering handwriting.
  • Built a dataset of scanned documents for handwriting recognition.
  • Ran experiments on handwriting recognition in Python.
Technologies: Python, Java

Subjective Image Captioning

The goal of this project was to automatically generate subjective captions for images.

To this end, we ran a crowdsourcing study to analyze how humans naturally caption images and developed machine learning methods for generating captions such as "Cute dog in a nice park."

Multimodal Social Media Analysis

Using computer vision and natural language processing to detect problematic content on Twitter.

Python-based Organizer

https://gitlab.com/blandfort/organizer
A light-weight organizer for taking notes and synchronizing them with a web server in an encrypted format.

Information Extraction From Documents

Designed and implemented a pipeline for automatic information extraction from scanned documents, using machine learning (NLP). This included the implementation of automated tests for the pipeline, optimizing the extraction service, and making it production-ready.

ML Pipeline for Biomarker Discovery

A Python-based API to create knowledge graphs from biomedical data and identify entities of interest from these graphs using machine learning. Available biomedical data included measurements from patient studies (multi-omics), public databases, and causal relations.
2016 - 2020

Ph.D. in Cognitive Science

TU Kaiserslautern and DFKI - Kaiserslautern, Germany

2013 - 2015

Master of Science Degree in Mathematics

TU Kaiserslautern - Kaiserslautern, Germany

2009 - 2013

Bachelor of Science Degree in Mathematics

TU Kaiserslautern - Kaiserslautern, Germany

Libraries/APIs

Scikit-learn, NumPy, Natural Language Toolkit (NLTK), X (formerly Twitter) API, PyTorch, TensorFlow, Matplotlib, SciPy

Tools

Git, GitLab

Languages

Python, SQL, PHP, Java

Platforms

Jupyter Notebook, Linux, Docker, Google Cloud Platform (GCP), Amazon Web Services (AWS)

Paradigms

Data Science, Functional Programming, Object-oriented Programming (OOP)

Storage

MySQL, PostgreSQL, Elasticsearch

Frameworks

Flask

Other

Artificial Intelligence (AI), Research, Natural Language Processing (NLP), Computer Vision, Deep Learning, Machine Learning, Algorithms, Generative Pre-trained Transformers (GPT), Teamwork, Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNNs), OCR, Web Scraping, Crowdsourcing, Neural Networks, Mentorship & Coaching, Annotations, Knowledge Graphs

Collaboration That Works

How to Work with Toptal

Toptal matches you directly with global industry experts from our network in hours—not weeks or months.

1

Share your needs

Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2

Choose your talent

Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3

Start your risk-free talent trial

Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.

Top talent is in high demand.

Start hiring