Tobias Plötz, Developer in Griesheim, Hesse, Germany
Tobias is available for hire
Hire Tobias

Tobias Plötz

Verified Expert  in Engineering

Machine Learning Developer

Griesheim, Hesse, Germany
Toptal Member Since
June 7, 2022

Tobias is a machine learning consultant focusing on computer vision and text analytics. He is experienced in identifying impactful data science use cases and driving projects from ideation to product in international team setups. Tobias values impact over hype, looking for the solution that provides the best fit for the problem at hand. He holds a Ph.D. in computer vision, having published several papers at top-tier conferences.



Preferred Environment

PyCharm, MacOS, Visual Studio Code (VS Code), Amazon Web Services (AWS), Git, Linux, Windows, Python, TensorFlow, PyTorch

The most amazing... system I've built is running multiple recognition stages to analyze millions of patents and extract previously inaccessible chemical information.

Work Experience

Senior Data Scientist

2019 - PRESENT
Merck KGaA
  • Built a computer vision pipeline analyzing millions of patents and extracting previously inaccessible chemical information.
  • Built a semantic search engine based on state-of-the-art open source NLP models to search different corpora with up to multi-million documents, including a question-answering capability leveraging GPT-3.
  • Created a smart search system enabling users to quickly set up personalized document retrieval systems on large document collections to cut down manual screening efforts.
  • Consulted internal stakeholders on data science projects, from use case identification and solutioning to implementing an MVP and productizing the solution.
  • Educated peers on foundational topics in machine learning and cutting-edge research.
  • Improved internal development best practices by monitoring the machine learning and data science tool landscape.
Technologies: Deep Learning, Amazon Web Services (AWS), Spark, PyTorch, Scikit-learn, Agile, Machine Learning, Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), Computer Vision, Data Science, Pandas, Scripting, Technical Hiring, Interviewing, Code Review, PySpark, Image Processing, Large Language Models (LLMs), Generative Pre-trained Transformer 2 (GPT-2), OpenAI

Computer Vision System for Chemical Data Extraction
Within a cross-functional team of data scientists, full-stack developers, and business experts, I was driving the conception and technical implementation of a multi-stage computer vision system for turning depictions of chemical compounds into a machine-readable form. The system works by first detecting drawings of molecules within each page of a document, e.g., a patent. Then, the drawing is parsed into its constituents which are finally merged into a molecular graph representing the chemical compound.

Our solution is powered by modern deep learning techniques and enables the recognition of small and very large molecules. Our solution allows searches for already patented molecules by automatically screening millions of patents and extracting chemical information therein.

We focused on quickly building an MVP and iterating from there in an agile framework during development.

Automated Screening of Large Document Collections

I built a machine learning system that automatically detects relevant documents crawled from the internet regularly.

As a special twist to this project, the systems need to adapt to each user's preference of what constitutes a relevant document while avoiding a lengthy training process and providing highly accurate predictions from the start.

To meet these goals, I employed weakly supervised learning techniques that effectively allowed us to set up an accurate user-specific classifier in less than an hour. Thus, the system could provide value to the user right away, cutting down on manual screening efforts while continuously improving through user feedback.

Neural Nearest Neighbors Networks
In this research project, I proposed a novel, a differentiable nearest neighbor lookup that can be used as a layer in any neural network. This research was published as a conference paper at NeurIPS 2018, one of the most renowned venues for machine learning research.

In my paper, the neural nearest neighbors layer is used mainly in the context of image restoration. Other researchers have applied the layer to a multitude of different problems like 3D reconstruction, graph learning, or deriving model explanations. Neural nearest neighbors generalize the well-known transformer module that powers state-of-the-art research in natural language processing and computer vision.

Semantic Search and Question Answering System

I have built a semantic search engine based on state-of-the-art open source NLP models to search different corpora with up to multi-million documents. This approach drastically improves the search experience upon keyword-based search by allowing users to pose natural language queries. The system also can extract answers based on relevant documents using either open source NLP models or GPT-3. In this project, I was instrumental in driving the implementation of a reusable technology stack, as well as consulting internal stakeholders on potential applications of the system.
2014 - 2019

Ph.D. Degree in Computer Science

TU Darmstadt - Darmstadt, Germany

2011 - 2014

Master's Degree in Computer Science

TU Darmstadt - Darmstadt, Germany

2008 - 2011

Bachelor's Degree in Computer Science

TU Darmstadt - Darmstadt, Germany


PyTorch, Scikit-learn, TensorFlow, Pandas, PySpark, SpaCy


PyCharm, Git, Gensim






Data Science, Agile


MacOS, Visual Studio Code (VS Code), Amazon Web Services (AWS), Linux, Windows


Computer Science, Machine Learning, Computer Vision, Artificial Intelligence (AI), Deep Learning, Image Recognition, Natural Language Processing (NLP), Image Processing, OpenAI, Generative Pre-trained Transformers (GPT), Large Language Models (LLMs), Generative Pre-trained Transformer 2 (GPT-2), Research, Scripting, Natural Language Queries, Technical Hiring, Interviewing, Code Review

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.


Share your needs

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

Choose your talent

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

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