The Business Line Radio Frequency Processing is enabling the car to sense its environment for advanced driver assistance toward autonomous driving and zero road fatalities and supporting the entire automotive chain from antenna to speakers. In this exciting role, you will be challenged by taking your part in the future of Automotive.
In our Car Radio and Autonomous Driving products, power dissipation becomes more and more critical. This implies a deep analysis of different aspects from the system down to the design. In this assignment you will focus on different aspects with respect to power behavior by investigate if, with the help of ML, we can make a more accurate power estimation model for technology specific aspects using available tester data, estimator information and simulation data.
The main objectives for this thesis topic are as follows:
Analyze the tester and product measured data of existing devices
Evaluate and categorize the data for proper data handling
Determine the input parameters for boundary settings
Build a ML model based on measured data, estimator info and simulation data
Research on ML model stacking using multiple output parameters
Evaluate the model(s) based on existing and new designs data and results
WHAT’S IN IT FOR YOU
Ability to develop your skills (technical, soft skills, communication, etc.)
Gaining experience in a multinational and diverse environment
Possibility to become part of NXP’s Young Professional Talent Pool
Working on real assignments which contribute to NXP’s objectives
WHO ARE WE
We are a team of 20 engineers located in Nijmegen. You will be cooperating closely with four members of our thermal competence team.
Master student in Electrical Engineering / Computer Science or related field
Some affinity with complex designs
Affinity and knowledge of ML methods
A basic level of analysis capabilities in the field of power and thermal aspects
Eagerness to learn new tools
Good communication skills in English (both verbal and written)
Pro-active, high energy, open-minded, eagerness to learn
Fulltime (40 hours per week) for a duration of a minimum of six months up to 12 months (internship and thesis combination is possible).
Please note that in order to be considered for an internship/working student, you need to be registered as a student during the entire period.