About the job
Our Mission
At Vertical Aerospace, we are at the forefront of transforming electric aviation. Our groundbreaking eVTOL (electric vertical take-off and landing) aircraft, the Valo, aims to establish a new benchmark for safety in air travel while achieving 'zero emissions'.
We are committed to redefining aerospace standards, moving away from outdated practices to innovate and grow as a scaling SME. Over the next few years, we anticipate significant growth as we strive to achieve airliner-level safety certification by 2028 and commence operations with our airline partners.
Your Role
As a Data Scientist, you will collaborate closely with our engineering teams to create models that enhance design, testing, and operational decision-making. This includes developing and validating predictive models such as battery lifespan predictions and surrogate models for load modeling.
You will be responsible for taking concepts through to deployable solutions, partnering with data engineers to ensure that your models are supported by robust data pipelines and integrated seamlessly into engineering workflows. A strong emphasis will be placed on practical application, ensuring that models are interpretable, validated, and compliant with certification standards.
Key Responsibilities
Develop and validate predictive models for various engineering and operational applications, including performance forecasting and reliability assessments.
Construct surrogate and approximation models to simplify complex systems and simulations, facilitating quicker and more scalable analyses.
Collaborate with engineering teams to understand physical systems and translate them into data-driven models.
Analyze extensive time-series datasets from flight and testing environments.
Work with data engineering to ensure reliable data ingestion, transformation, and accessibility for modeling, enabling advanced analytics.
Deploy models into production environments or engineering toolchains, ensuring their maintainability and usability.
Ensure models are well-documented, explainable, and aligned with engineering and certification standards.
Contribute to the creation of reusable modeling frameworks and methodologies across the organization.
