Timo Denk

Timo

Hi there!


My name is Timo, I am a Software Engineer based in San Francisco. At Google DeepMind I work on Gemini, specifically its audio generation and understanding.

In my leisure time I like to fly around, 3d print, and occasionally work on artsy projects. Besides that I am into classical music and learn playing the violin. Sports-wise road cycling and hiking are my favorite activities.

To get a deeper idea of who I am you are invited to take a look at my values. An overview of recent projects is given at blog.timodenk.com.

Professional Skills

Software Engineering

Machine Learning

Hardware

Resume

Professional
Google
San Francisco · since June 2021
Applying machine learning to music generation (see MusicLM) and music recognition (Now Playing)
Denk Development
June 2016 - Dec 2021
Mainly microcontroller programming (Arduino, Teensy, etc.) and electronics, as well as managing the company
Zalando
Berlin · Oct 2019 - May 2021
Outfit generation with methods from natural language processing
SAP
Walldorf/Berlin · Sep 2016 - Sep 2019
Cooperative education student, working in backend engineering and machine learning departments
Hatchery
Stuttgart · Nov 2015 - Aug 2016
Full-stack web development, start-up environment, and customer contact
Education
Baden-Wuerttemberg Cooperative State University
Karlsruhe · Sep 2016 - Sep 2019
BSc in Computer Science; graduated with grade A (top 10%)
Technisches Gymnasium
Waiblingen · Sep 2013 - July 2016
High school diploma; graduated with 1.0 (valedictorian)

Blog Articles

I am occasionally publishing articles at blog.timodenk.com.
Here are some selected ones:

Publications

(for a full list see my Google Scholar profile)

Timo Denk, Yu Takagi et al. (Jul 2023): Brain2Music: Reconstructing Music from Human Brain Activity. [paper] [samples]

Andrea Agostinelli, Timo Denk et al. (Jan 2023): MusicLM: Generating Music From Text. [paper] [samples] [data]

Timo Denk, Ana Peleteiro Ramallo (Dec 2020): Contextual BERT: Conditioning the Language Model Using a Global State. Workshop paper accepted at the COLING 2020 workshop TextGraphs-14. [paper] [presentation]

Timo Denk, Christian Reisswig (Sep 2019): BERTgrid: Contextualized Embedding for 2D Document Representation and Understanding. Best Paper Award at the NeurIPS 2019 Document Intelligence workshop. [paper] [presentation] [thesis]

Other Platforms

Contact

simssosdenk@gmail.com
© Timo Denk · Legal