ML engineer for @MSFTQuantum. All things ML / chemical reactions / QC. Previously @EPFL @MSFT_Research @imperialcollege @EdinburghChem
Lausanne, Switzerland
Joined July 2021
- Tweets278
- Following428
- Followers506
- Likes574
Puck van Gerwen retweeted
🚨 Our team at GDM is hiring a research engineer to work on topics around RL, post-training + materials science! Role is based in Mountain View. DMs open if you have questions.
Puck van Gerwen retweeted
Our new @ChemRxiv preprint: AIMNet2-rxn: A #MachineLearning Potential for Generalized Reaction Modeling on a Millions-of-Pathways Scale! #compchem Collaboration with @ProfSavoie group. Funded by @USNavyResearch under #MURI program
chemrxiv.org/engage/chemrxiv…
Puck van Gerwen retweeted
🚀 After two+ years of intense research, we’re thrilled to introduce Skala — a scalable deep learning density functional that hits chemical accuracy on atomization energies and matches hybrid-level accuracy on main group chemistry — all at the cost of semi-local DFT. ⚛️🔥🧪🧬
Puck van Gerwen retweeted
Great collaboration with @SchwallerGroup ! Congratulations to the BoLudo team 👏 and looking forward to what comes next :) @EPFL_CHEM_Tweet @EPFL_en @NCCR_Catalysis @pschwllr @6ojaHa
pubs.acs.org/doi/10.1021/jac…
Puck van Gerwen retweeted
Our engineer team at @MSFTResearch AI for Science is hiring a Senior Research Engineer in Berlin, Amsterdam, or Cambridge (UK). We’d love to see candidates with industry experience (or equivalent) who love infrastructure, big data, debugging, profiling, and optimization of pipelines and (ML) code, ideally with some background in science. Great opportunity to work on AI for Science at scale. Apply via the following link:
jobs.careers.microsoft.com/g…

Puck van Gerwen retweeted
🐫Just over two weeks left to apply for the Chemical and Materials Machine Learning School 2025. ML, MLIPs, GNNs, GenAI - so many cool acronyms explained!! Sponsored by @aichemyhub @PSDI_UK @CCP5UK @UKRI_News 🔗 aichemy.ac.uk/ml-training-sc… 🐫psdi.ac.uk/event/cammls-2025…
Puck van Gerwen retweeted
Our internship position closes in 2 days on 31 Oct. Apply now if you want to work with us on AI for materials design at MSR AI for Science: jobs.careers.microsoft.com/g…
#ai4science #ml #materials #internship #mattergen
Puck van Gerwen retweeted
📣We have a tenure-track faculty opening in Responsible AI at @CSatETH:
ethz.ch/en/the-eth-zurich/wo…
@ETH_en is a vibrant environment for AI research with the @ETH_AI_Center etc.
Please help spread the word!
Puck van Gerwen retweeted
We are #hiring #PhD students via the #ELLIS PhD Program!
Interested to work on (generative) #AI method development to advance personalized medicine? Located at the School of Computer Science and Life Sciences at @EPFL🇨🇭and part of the @EPFL_AI_Center, we are closely collaborating with researchers from biology and university hospitals.
So lots of #data, lots of #compute, and lots of problem solving 🔧. For more information, visit our webpage (bunnelab.com) and reach out regarding projects, co-supervision, or other questions!
The #ELLISPhD application portal is now open! Apply to top #AI labs & supervisors in Europe with a single application, and choose from different areas & tracks.
The call for applications: ellis.eu/news/ellis-phd-prog…
Deadline: 15 November 2024
#PhD #PhDProgram #MachineLearning #ML
Updates! Today I graduated my PhD from @EPFL with @corminboeuf_lab. You can find me at @Azure in January working with @Nabbelbabbel. Until then I will enjoy some travel and a slower pace of life 🌟
Puck van Gerwen retweeted
📢 Another faculty position at Imperial, this time in data-driven characterisation of materials! Open to researchers who leverage artificial intelligence to analyse large datasets from cutting-edge characterisation techniques. Applications close 19th Oct. shorturl.at/Htotp
Puck van Gerwen retweeted
Submit to @LogConference! You will receive high-quality reviews and feedback and get the chance to present in the graph machine learning’s community annual conference!
Less than a day to go to submit abstracts to @LogConference 2024 -- send your work to LoG and we'll ensure you get expert reviewers who work in the same sub-field :)
logconference.org/cfp/
Puck van Gerwen retweeted
Phd students: submit your projects for a chance to get an NVIDIA fellowship!
Time until Sept 11!
And yes: applications in digital biology are very welcome!
research.nvidia.com/graduate…
Puck van Gerwen retweeted
Introducing Neural Electron Real-space Density (NERD) models! 🧠 You’ve solved the electronic Schrödinger equation using PauliNet or Psiformer - what next? Important properties come from the 1-electron density (the marginal #MachineLearning)
arxiv.org/abs/2409.01306
Puck van Gerwen retweeted
There is one regular PhD position for Fall 2025 available at LCSO and the application process is now open! If you are interested please read carefully about our group and how to apply on our website:
epfl.ch/labs/lcso/group/open…
Puck van Gerwen retweeted
A 2-year postdoc position in computational chemistry & ML is available in our group at @psl_univ (more info about the project below). Applications can be submitted through the CNRS job portal: emploi.cnrs.fr/Offres/CDD/UM…. Deadline: Sept 24th. Retweets are appreciated! #chempostdoc
Puck van Gerwen retweeted
3DReact: Geometric Deep Learning for Chemical Reactions
pubs.acs.org/doi/10.1021/acs…
@puckvg @54briling @_bunnech @_vsomnath @ruben_laplaza @arkrause @corminboeuf_lab @ruben @NCCR_Catalysis @nccr_marvel @EPFL_en
#JCIM Vol64 Issue15 #MachineLearning #DeepLearning
Puck van Gerwen retweeted
Work with @ProfvLilienfeld . It’s going to be great fun and innovative science
Please share/repost!!! We're still looking for someone outstanding with QM & simulation or #COMPCHEM background to join our AI & Automation team as a permanent scientist at @acceleration_c @UofT in order to learn and use #MachineLearning in collaboration with @VectorInst! DM me if interested yourself!
Puck van Gerwen retweeted
Another excellent molecular design study by Jeff (@JeffGuo__)!
In this work, he shows it's possible to directly optimize for synthesizability in generative molecular design using retrosynthesis models. His approach efficiently generates drug-like molecules optimized for multiple parameters and deemed synthesizable, even under tight computational constraints.
Check out his tweet for preprint and code. 👇
@NCCR_Catalysis @EPFL_CHEM_Tweet @EPFL_AI_Center
Molecular generative models can *directly* optimize for synthesizability using retrosynthesis models!
Check out initial results which can be an alternative to synthesizability-constrained generation
Pre-print: arxiv.org/abs/2407.12186v1
Code: github.com/schwallergroup/sa…
(1/2)
Puck van Gerwen retweeted
For those of you attending #ICML2024 , please consider joining our workshop on
ML for Life and Material Science, July 26th
Featured speakers/panelists include @mmbronstein and @HochreiterSepp !
ml4lms.bio/
