About this role
Summary: Join Fusionality to build and maintain data pipelines for fusion energy research, developing ML-assisted labelling and event detection systems. The role involves transforming large, heterogeneous experimental data into high-quality datasets and collaborating with physicists and engineers to support real-time monitor...
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.
- Proficient using Agentic coding and other modern AI technologies to accelerate your work, while remaining accountable for the outcomes.
### The following are an advantage but not strictly required:
- Human-in-the-loop labelling tools and workflows.
- Pipeline Orchestration (e.g. Dagster, Airflow, Prefect) and data versioning (e.g. DVC, lakeFS).
- Data from large physics experiments: fusion, accelerators, astronomy, or exposure to fusion data systems (MDSplus, IMAS).
What we offer
- Play a key role at a dynamic, fast-growing startup, shaping the technical solutions and products from the ground up.
- Build cutting edge technology to monitor and control plasmas in real fusion devices, working side-by-side with leading plasma and control experts.
- Great working conditions, located in Lausanne, Switzerland, a city and country known for its high quality of life.
- Competitive salary and equity compensation, matched to level of seniority, and benefits including immigration assistance.