AI/ML Engineer at Riverlane, Delft, NL. A mid-level full time position in the Research team, listed under research. The salary range for this role is broad, as we are able to consider varying levels of experience. Any offer made will carefully take into account level of experience (including relevant industry experience), transferable relevant skills and previous relevant achievements. About the role
As an AI/ML Engineer at Riverlane, you will apply artificial intelligence (AI) and machine learning (ML) to one of the defining challenges in quantum computing: quantum error correction (QEC). You will join our newly established R&D team in Delft, which focuses on using AI and ML to advance the state of the art in QEC and on deploying the resulting models in our QEC stack. As part of a highly collaborative research group, you will bring ML expertise and work together with QEC researchers to develop novel solutions at the intersection of these fields. You will build, train and test models on real experimental data, and where your impact comes through the quality of your engineering, your ability to turn ideas into working tools and your ability to collaborate with colleagues from a range of disciplines. You will tackle genuinely novel problems and help define how AI will shape the future of quantum error correction. What you will do
In this role, you will apply your ML expertise and working knowledge of QEC to design, build and improve the AI models that power our next-generation QEC tools. You will collaborate closely with QEC researchers, other AI engineers and software engineers to turn promising ideas into intelligent, adaptive and scalable solutions. From early-stage prototyping through to training, optimisation and deployment, you will play a key role in taking AI models for QEC from research into production-ready technology. Your work will vary, but typical activities include
Design, train and evaluate ML models for QEC tasks such as decoding, calibration and noise characterisation, using both simulated and real experimental data.
#J-18808-Ljbffr
