TDK InvenSense Offre de stage – Deep Neural Network for Microcontrollers- A no Compiler Approach About TDK InvenSense Founded in 2003, InvenSense Inc., a TDK Group Company, is the world’s leading provider of MEMS sensor platforms. InvenSense’s vision of Sensing Everything™ targets the consumer electronics and industrial markets with integrated Motion and Sound solutions. Our solutions combine MEMS (micro electrical mechanical systems) sensors, such as accelerometers, gyroscopes, compasses, and microphones with algorithms and firmware that intelligently process, synthesize, calibrate and classify the output of sensors. InvenSense’s motion tracking, audio and location platforms, and services can be found in many of the world’s largest brands including smartphones, tablets, wearables, drones, gaming devices, internet of things, automotive products, and remote controls for smart TVs. InvenSense is headquartered in San Jose, CA and has offices in Boston, China, Taiwan, Korea, Japan, France, Canada, Slovakia, and Italy. We’re looking for top-notch students to join our global intern team. If you’re interested in being a part of our journey and helping us grow to become the leading provider of SoC platform solutions, we want to hear from you. Internship Description We are looking for motivated students to join our Algo Motion team at TDK/InvenSense, the world’s leading provider of MEMS sensor platforms (accelerometers, gyroscopes, magnetometers, and microphones). You will join our small and friendly SW team, located in Grenoble city. Traditionally, we train AI models using real sensor data acquisition, algorithms then are embedded into earbuds, watches or glasses. Some of these new algorithms are now available on the market, in association with TDK /Invensense IMUs (SmartMotion® | TDK InvenSense). However, the dependency on the data is still a pain point for Machine Learning techniques. So, we are working on data augmentation techniques, to reduce the cost and delays of the Data Acquisition Tasks. In this Internship, we want to explore and test using a Mechanical Simulator generating synthetic IMU data that a real sensor would generate when attached to a rigid body experiencing trajectories and experiments. This would allow us to generate as much data as we want to feed an AI model. We would like to start with one example such as Free fall detection: smartphones use several micro mechanical devices (MEMs), accelerometer, gyrometer, autofocus lenses. If device falls, it is a good idea to trigger all sensible parts to take immediate action to prevent damage when hitting the ground, for example by locking moving parts. The internship will allow to explore these different stages: Simulation of Free fall data, using a python library; free fall physics can be surprising, for example: https://fr.wikipedia.org/wiki/Effet_Djanibekov . We need to select an appropriate physics simulation library. Acquisition of free fall data on real devices, and comparison. We will design and print 3D board holders and enclosures to protect our boards vs. shocks. Design, train and test a Neural network that could detect, with a small latency, the falling state. Ideally the event could be detected and triggered before the 0.5m fall. Implementation in C using our framework and live demo on a TDK device During his journey, the intern will also contribute to our AI tool, by testing and optimizing the best neural network architecture and enhancing the C Neural network code. Required skills: Programming and optimization in C/Python, Git. Knowledge/Interest in Rigid Bodies Mechanical Simulator. Some knowledge and interest in machine learning methods. Desire for running experiments. Pragmatic mindset, autonomy and creativity. Qualifications : Niveau Bac+5 Dates: Janvier/Fevrier 2026 - Juin/Juillet 2026 Durée du stage: 6 mois Localisation: Grenoble (quartier Europole) Merci d’envoyer votre curriculum vitae ainsi que votre lettre de motivation a : etienne.deforas@tdk.com TDK – InvenSense MEMS Sensor Business Group Sensor System Business Group 22 Avenue du Doyen Louis Weil 38000 GRENOBLE www.invensense.com