Mika Senghaas
Research engineer at Prime Intellect; first author of the INTELLECT-3 and PRIME-RL reports
- Research engineer, Prime Intellect12
Mika Senghaas is a research engineer at Prime Intellect. Senghaas is the first named author of the INTELLECT-3 technical report, on a mixture-of-experts model post-trained with large-scale reinforcement learning, and of the PRIME-RL report on asynchronous, decentralized reinforcement learning training.13
Research and engineering
Senghaas works as a research engineer at Prime Intellect, and the publications listed on Senghaas's site focus on decentralized training and reinforcement learning. Other listed work includes DiLoCo-SWARM, a report on scalable decentralized training.1
Senghaas is first author of the PRIME-RL report and of SYNTHETIC-2, and a co-author of the INTELLECT-2 report, which describes a reasoning model trained through globally decentralized reinforcement learning. Senghaas is the first named author on the INTELLECT-3 technical report (2025), whose model was trained with prime-rl and environments from the verifiers library.1435
Work
INTELLECT-3Open weights
First named author of the INTELLECT-3 technical report (2025), which describes the model's supervised fine-tuning and large-scale reinforcement learning starting from GLM-4.5-Air-Base.31
prime-rlOpen-source code
First author of the PRIME-RL report on asynchronous and decentralized reinforcement learning training at scale, which accompanies the prime-rl repository.16
SYNTHETIC-2 (external site: mikasenghaas.de)Open data
First author of SYNTHETIC-2, a Prime Intellect project on distributed synthetic data generation for verified reasoning.1
Career timeline
2025
First author of the PRIME-RL report on asynchronous and decentralized reinforcement learning training.1
2025
First author of SYNTHETIC-2, a project on distributed synthetic data generation for verified reasoning.1
May 2025
Co-authored the INTELLECT-2 technical report.4
Dec 2025
Posted the INTELLECT-3 technical report as first named author.3
Related people
More sourced profiles at the same organization, in the same field, or from the same school.
- Johannes HagemannAlso at Prime Intellect
- Edward BeechingLanguage models
- Jakub PachockiLanguage models
- Susan ZhangTraining systems
- Weizhu ChenLanguage models
- Akshita BhagiaLanguage models
- Albert JiangLanguage models
- Alexander WettigLanguage models
- Aravind SrinivasLanguage models
- Arthur MenschLanguage models
- Barret ZophLanguage models
- Beren MillidgeLanguage models
Is this you?
Profiles cover public professional work only, and every line cites a source. If something is out of date, missing or wrong, send a correction with a link to an official page and we will update it. Suggest a correction
Add this badge to your website or GitHub profile README. It links back to this page. It is not an endorsement or a rating.
Markdown (for a README)
[](https://unitedstatesofamericasuperintelligence.com/people/mika-senghaas/)
HTML
<a href="https://unitedstatesofamericasuperintelligence.com/people/mika-senghaas/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/profile.svg" alt="Mika Senghaas — Profile on USASI" height="20"></a>
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.