Post Doc Research

Technology, Data & Digital · Data, AI & Analytics · Data Science · Machine Learning

In short

Microsoft Research AI for Science is looking for a postdoctoral researcher in computational chemistry to contribute to the generation of data for Skala, a deep-learning exchange-correlation functional for DFT. The role involves designing and implementing methods for generating diverse molecular structures and building automated data-generation workflows in Python.

Responsibilities

Design, implement, and scale methods for generating chemically diverse molecular structures, including covalent, non-covalent, bond-dissociation paths, and reaction geometries/transition states.
Combine and extend structure-generation approaches like graph-based, fragment-based construction, conformer/reaction-path sampling, and molecular dynamics/metadynamics.
Define sampling and selection strategies to ensure new data fills gaps in chemical space and quantify overlap with existing datasets.
Build and maintain robust, automated, reproducible data-generation workflows in Python on shared codebases.
Collaborate with colleagues on data generation, model development, and deployment to inform priorities for future datasets.
Contribute to the efficiency of the data-generation pipeline, including exploring GPU-accelerated electronic-structure methods for speed-ups.
Prepare technical papers, presentations, and open-source releases of research code and data.

Requirements

PhD in computational chemistry, theoretical chemistry, computational condensed-matter physics, or a related area, completed or close to completion (thesis submitted, or expected within 6 months of the start date), or comparable research experience.
Hands-on research experience with electronic-structure methods (DFT and/or semiempirical/tight-binding methods).
Hands-on research experience with generating, optimizing, or sampling molecular structures.
Proficiency in Python.
Experience with collaborative code development on shared codebases.
At least one peer-reviewed publication or preprint in computational chemistry or a related field.

Desired Qualifications

Experience developing or contributing to open-source scientific software (e.g., quantum-chemistry or atomistic-simulation packages).
Experience with extended tight-binding (xTB/GFN) methods.
Experience with conformer, reaction-path, or molecular-dynamics-based structure exploration.
Experience building computational-chemistry datasets, for example for training machine-learning models.
Experience with GPU-accelerated or high-performance computing for quantum chemistry.
Familiarity with wavefunction-based methods (e.g., coupled cluster) and thermochemistry or reaction-energy benchmarks.
Experience integrating methods into existing quantum-chemistry codes (e.g., ORCA, PySCF, CP2K).

Benefits

Access to substantial computational resources.
Results shared through publications and open-source releases.
Base pay: € 8,191.00 per month (Berlin)
Base pay: £ 6,655.00 per month (Cambridge)
Base pay: € 6,811.00 per month (Amsterdam)

Skills

PythonDFTmolecular dynamicsmetadynamicstight-bindingxTBGFNGPU acceleration

#computational chemistry#deep-learning#data generation#DFT#quantum chemistry#machine learning#Python#research

About Microsoft

Empowering every person and organization on the planet to achieve more

Every company has a mission. What's ours? To empower every person and every organization to achieve more. We believe technology can and should be a force for good and that meaningful innovation contributes to a brighter world in the future and today. Our culture doesn’t just encourage curiosity; it embraces it. Each day we make progress together by showing up as our authentic selves. We show up with a learn-it-all mentality. We show up cheering on others, knowing their success doesn't diminish our own. We show up every day open to learning our own biases, changing our behavior, and inviting…

See all open jobs at Microsoft Read more about Microsoft Website