Sd-25009 Postdoc On Machine Learning for Road Characterization

Description
**Temporary contract | 24 months | Belval**:
***:
**Are you passionate about research? So are we Come and join us**:
The Luxembourg Institute of Science and Technology (LIST) is a Research and Technology Organization (RTO) active in the fields of materials, environment and IT. By transforming scientific knowledge into technologies, smart data and tools, LIST empowers citizens in their choices, public authorities in their decisions and businesses in their strategies.

In 2024, LIST and GOODYEAR signed the second phase of their partnership, 2024-2029, building on the outcomes of their previous collaboration and entering new technological areas as well. GOODYEAR-LIST partnership 2.0 embraces Luxembourg's National priorities, such as Sustainability, Digital transformation and Circular economy, through the execution of six Strategic Research Programs: Data Science for Tires, Tire as a Sensor, End-of-Life Tire Valorization, Sustainable Materials for Non-Pneumatic Tires, Sustainable Materials for Next Generation of Pneumatic Tires, Structure-Process-Properties Relationships.

***:
**How will you contribute?**:
Do you have proven skills in data analysis, machine learning, as well as in mathematical and computational modelling?

You will have the opportunity to investigate innovative solutions using machine learning algorithms and predictive modelling techniques in the context of a collaborative project with Goodyear Luxembourg (one of our national industrial partners).

Road condition is an essential part of mobility which influences virtually all facets of driving and tire performances. That is why it is becoming a demanding strategic research area that significantly impacts the tire development industry. Mainly road conditions are characterized by the friction coefficient. However, it can be extended to study the granularity of the road surface, roughness, and holes. The prediction of the road conditions is linked to several external variables related to the weather conditions, road surface micro
- and macro-texture, tire properties, driving speed, and behaviours of road users. This project aims at studying different data sources such as TPMS data, high-speed wheel encoders, CAN data, accelerometer data, and acoustics data. In addition to other cloud-based data for weather-friction estimates and crowdsourced vehicle data for estimating road conditions.

Your specific activities will include (but are not limited to):

- Develop robust, production-grade machine learning solutions for predictive modelling and complex decision-support systems.
- Develop scalable and efficient ML pipelines using MLOps best practices.
- Address challenges related to real-world sensor data, such as faulty or missing data.
- Develop and implement techniques for data validation and consistency checks using real-world industrial datasets.
- Disseminate the project results through project reports and deliverables, scientific publications in journals and conferences and presentations at industry events.

**Education**:
**Required experience and skills**:

- Extensive experience in machine learning methods, tools, and platforms.
- Proficiency in Python, with demonstrated software development experience.
- Hands-on experience in MLOps, including the design and deployment of production-grade ML pipelines.
- Solid mathematical foundation, with knowledge of statistical analysis.
- Experience in using database systems (relational, data warehouse and data lake).
- Sound publication track record in relevant international conferences and journals.
- Ability to present research findings in a clear and concise manner through reports, presentations, and scientific papers.
- Experience of working in applied research projects preferably with industrial partners.
- Ability to work in teams geographically located in different partner’s facilities.
- Strong interpersonal and communication skills to collaborate effectively with cross-functional teams, stakeholders, and industry experts.
- Good communication skills.
- Good written and verbal communication skills in English is mandatory.

**Nice to have experience**:

- Statistical knowledge: Experience in uncertainty analysis, particularly in the context of large datasets and real-world statistical modelling.
- Road Condition Research: Knowledge and experience in the field of road condition research, including an understanding of road surface characteristics, friction coefficient, road texture, roughness, and related parameters. Familiarity with relevant research methodologies and techniques.
- Data Collection and Sensors: Familiarity with different data collection methods and sensors used to gather road condition data, including TPMS (Tire Pressure Monitoring System), high-speed wheel encoders, CAN (Controller Area Network) data, accelerometers, and acoustics data. Understanding of sensor technologies and their limitations.
- Experience in managing research projects, including planning, organizin