Machine Learning Engineer with Sensor Background

In this role, your primary focus will be designing, building, and deploying production-grade machine learning models that extract actionable insights from noisy, and multi-modal sensor data. Your key responsibilities will include:

• Model Development: Designing, training, and evaluating classical ML and deep learning architectures (e.g., CNNs, RNNs/LSTMs, Transformers) optimized for time-series forecasting, anomaly detection, gesture recognition, or spatial tracking.
• Advanced Architecture Design: Building and fine-tuning state-of-the-art Transformer-based models and Large Language Models (LLMs) adapted for sequential data (e.g., Time-Series Transformers, behavioral embeddings, and tokenized sensor streams).
• Signal Processing & Feature Engineering: Implementing digital signal processing (DSP) techniques; including filtering, windowing, fast Fourier transforms (FFT). To clean, calibrate raw, noisy sensor data and extract robust features.
• Edge & Embedded Optimization: Optimizing models for resource-constrained environments via quantization, pruning, and hardware-accelerated compilation (e.g., ONNX, TensorRT, TensorFlow Lite) for deployment on edge devices.
• ML Operations & Data Pipelines: Building scalable pipelines capable of handling massive volumes of streaming, asynchronous telemetry data, ensuring minimal latency and high throughput in production.
• Experiment & evaluation of sensors in various environments such as microphone, accelerometer, gyroscope, ultrasonic time of flight, pressure, magnetometer.
• Development: oversees product development, data collection, improvement and testing.
• Reporting: communicate complex technical information and analysis to extended team members and management.

At TDK we foster a collaborative and supportive engineering and business culture. Especially, as our algorithms are - an important but only a part - of the solution, collaboration between algorithm team, machine learning team, integration team, validation team and HW team is key to understand the system. Therefore, your ability to demonstrate excellent communication skills is critical as you interact with engineers from other teams (system, validation, embedded software development, and marketing), partners, and suppliers. In doing so, you will enjoy the opportunity to be visible and measurably contribute to the advancement of our technology and product lines., * MSc/Ph.D. in Computer Science, Signal Processing, Machine Learning (ML),

• 5+ years of experience in a similar industrial context of Sensor Systems, Machine Learning (ML), Deep Neural Network (DNN), Mechanical Modeling and Simulation, Acoustic, Algorithms.
• Exercised proven background in signal processing and Algorithms (on acoustic sensor, accelerometers, or other sensors …),
• Exercised experience in C language for embedded software production with industrial standards,
• Teamwork, SW development tools, GIT, Code Coverage Tools,
• Algorithm implementation and optimization methods,
• Proficiency in Python,
• Ability to lead solid innovation, characterize, debug and evaluate algorithms,
• Passionate, problem solver, autonomous, and team player,
• Enthusiasm to learn/share new methods and techniques within several technical areas,
• Very good English communication, and ability to work in an international, multicultural environment.

Reporting & Interactions

• Direct report to the local manager
• Frequent interactions with cross-functional teams including QA, platform, and tools, and with the extended team based in San Jose, California
• Bring Solid Data Driven and Experience driven Expertise to our SW Lead for our Business Unit(s). Report progress, advise solutions

American R&D Center (ARDC) is a central R&D organization of the TDK Group. Its mission is to contribute into the design of new products within TDK with the ambition to create new product lines. ARDC is working closely with InvenSense Inc., a TDK Group Company, who 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, Sound, UltraSound, Pressure, Gas solutions. InvenSense's motion tracking, audio, ultrasound, and services can be found in many of the world's largest and most iconic brands including smartphones, tablets, wearables, drones, gaming devices, internet of things, automotive products, and remote controls for smart TVs. Both ARDC & InvenSense are headquartered in San Jose, CA, and have offices in Boston, China, Taiwan, Korea, Japan, France, Slovakia, and Italy. We are looking for top-notch engineers to join our global team. If you're interested in being a part of our journey and helping us to create new product around sensors and machine learning, we want to hear from you. Mission and Opportunity Joining the ARDC Grenoble Team, you will bring your expertise in designing and building new Smart Platforms products (IoT devices with several sensor modalities) used to solve complex applications in various markets (consumer, robotics, industrial, health, automotive). In Grenoble, we're a group of 65 people working as a team for 15 years in SW R&D around sensor modalities. We're born and inserted in the Grenoble Hi Tech ecosystem and collaborating daily with the TDK-ARDC San Jose California SW team, contributing to elaborate products for the biggest hi-tech companies and markets. Our SW R&D Team is about 30 people across Grenoble and San Jose, and the team in Grenoble is about 18 people.