Data/ML engineer, fusion data

About this role

Fusionality is building the measurement, simulation, and control stack for the fusion energy reactors of the future. Spun out of EPFL’s Swiss Plasma Center and backed by top investors, our technology enables reliable operation, real-time monitoring, and analysis of high-temperature plasmas in fusion devices. We are founded by world-class experts at the intersection of fusion physics, advanced control, and AI (ex-Google DeepMind, EPFL).

We are assembling a founding engineering team in Lausanne to build our core technology platform. We are looking for a Data / Machine Learning Engineer to join our team. This job is for you if you like turning large, messy, heterogeneous experimental data into clean, labelled, trustworthy datasets. You have done this with scientific or industrial sensor data. Familiarity with fusion is a plus but not a strict requirement.

Responsibilities Build, maintain and run pipelines that bring experimental fusion data into high quality, consistent, documented, versioned datasets. Develop ML-assisted labelling and event detection (e.g. disruptions, MHD activity, diagnostic faults), using weak supervision, active learning and anomaly detection. Own data quality and provisioning: provenance, calibration metadata, automated validation. Manage and facilitate access for the rest of the team.

Work with physicists validating the datasets & labels. Work with our computational scientists and control engineers, who build models and controllers on these datasets, and with customers to understand and integrate their data. Requirements Hands-on experience building data pipelines for large scientific or industrial time-series data formats (e.g. HDF5, Parquet, Zarr). Proficiency in designing, querying and optimizing SQL and noSQL database systems and familiarity with Time Series databases such as TimescaleDB, InfluxDB.

Experience in applying ML techniques to time series in Python (PyTorch or JAX): sequence models, anomaly and event detection, semi- or weakly-supervised labelling. Solid software engineering habits: testing, reproducibility, data versioning are second nature to you. Evidence of independent work at the highest level: a PhD thesis and/or published code that is used by others, or an industry project you owned. You should be comfortable designing data architectures independently from day 1.