Machine Learning Scientist - Synthesis Planning and Optimization

Roche

1d•$147,600 - $310,800•Onsite

About The Position

Join the small-molecule team within AI for Drug Discovery (AI4DD), formerly Prescient Design, at Roche and Genentech’s Computational Sciences Center of Excellence as a Machine Learning Scientist / Senior Machine Learning Scientist in Synthesis Planning and Optimization. You will build ML methods that design molecules we can actually make — closing the loop between generative design and automated synthesis. Develop and advance machine learning methods for synthesis-aware molecular design across retrosynthesis, synthesis planning, molecular generation, and search in synthesizable chemical spaces. Integrate proprietary reaction and biochemical data to design the next generation of synthesis-aware models and workflows for hit finding and optimisation. Build robust, scalable pipelines for active-learning loops that interface directly with automated and high-throughput synthesis platforms. Design novel batch synthesis-planning algorithms that maximise chemical-space coverage, information gain and experimental efficiency. Drive scientific impact through publications, open-source releases, and conference talks.

Requirements

Deep machine-learning expertise with a strong foundation in linear algebra, probability and optimization.
Hands-on experience in modern machine learning approaches such as graph-neural networks, sequence/language models and reinforcement learning.
Familiarity with chemistry concepts relevant to synthesis planning and molecular optimisation.
Familiarity with small molecule data and cheminformatics toolkits such as RDKit or Openeye.
Fluency in Python and experience with modern ML frameworks like PyTorch or JAX.
Experience with scientific software development.
A PhD or equivalent research depth in machine learning, computational chemistry, chemical engineering or a related quantitative field such as physics or statistics.
A record of scientific excellence evidenced by journal and conference publications or a public portfolio of relevant projects (e.g. hosted on GitHub/GitLab).

Nice To Haves

Experience with retrosynthesis or synthesis-planning models.
Experience with automated/high-throughput synthesis.

Responsibilities

Develop and advance machine learning methods for synthesis-aware molecular design across retrosynthesis, synthesis planning, molecular generation, and search in synthesizable chemical spaces.
Integrate proprietary reaction and biochemical data to design the next generation of synthesis-aware models and workflows for hit finding and optimisation.
Build robust, scalable pipelines for active-learning loops that interface directly with automated and high-throughput synthesis platforms.
Design novel batch synthesis-planning algorithms that maximise chemical-space coverage, information gain and experimental efficiency.
Drive scientific impact through publications, open-source releases, and conference talks.