Huidige banen gerelateerd aan Postdoc Federated Learning for Autonomous Vehicle Perception and Prediction - Delft - TU Delft
-
Postdoc Ai-enabled and Sensor-based Autonomous
2 maanden geleden
Delft, Nederland TU Delft VoltijdPostdoc AI-enabled and Sensor-based Autonomous Material Identification- Job description The construction sector is responsible for roughly 39% of global greenhouse gas emissions [Moschen-Schimek; Huber-Humer; 2023]. To achieve a sustainable and resilient society, it is crucial to comprehend the performance of existing built works and their potential for...
-
Postdoc Data-driven Prediction of Human Body Motion
5 maanden geleden
Delft, Nederland TU Delft VoltijdPostdoc Data-driven Prediction of Human Body Motion in Automated Vehicles- Job description The potential discomfort and motion sickness experienced by passengers during automated journeys pose a significant challenge to their widespread adoption. Envisaged automated vehicle (AV) designs and their driving behavior are expected to provoke motion sickness and...
-
PhD Decentralised Machine Learning
2 maanden geleden
Delft, Nederland Technische Universiteit Delft (TU Delft) VoltijdPhD Decentralised Machine Learning 36-40 hours per week Challenge : Developing and building a fully decentralised video search engine.Change : Eliminating the need for servers when developing machine learning.Impact : Safe machine learning benefiting billions of users.Job description Billions of mobile devices mean unprecedented computing power and a surge...
-
Postdoc in Wireless Communication and Sensing
5 maanden geleden
Delft, Nederland TU Delft VoltijdPostdoc in Wireless Communication and Sensing- Job description We are excited to announce an opportunity for a highly motivated postdoc in the field of Wireless Communication and Sensing. If you're passionate about pushing the boundaries of technology, this is your chance to make a significant impact in areas such as: - Physical layer optimization - Signal...
-
Postdoc Efficient Modeling of Cracking Between
2 maanden geleden
Delft, Nederland TU Delft VoltijdPostdoc Efficient Modeling of Cracking between Bonded Thermoplastic Composites- Job description Thermoplastic composites are the lightweight materials of the future, supporting the automotive and aerospace needs to reduce fuel consumption and extend vehicle range. Optimal usage of these materials requires fast and reliable integration techniques to...
-
Postdoc Position 3D Representation for Controlling
5 maanden geleden
Delft, Nederland TU Delft VoltijdPostdoc Position 3D Representation for Controlling Composite Fabrication Process- - 3D Representation for Controlling Composite Fabrication Process_ Job description We are looking for a passionate Postdoctoral researcher to join our team and contribute to a cutting-edge project at the intersection of 3D Computer Vision, Composite Fabrication and Aerospace...
-
Postdoc in Wireless Communication and Sensing
2 maanden geleden
Delft, Nederland TU Delft VoltijdPostdoc in Wireless Communication and Sensing- Job description We are excited to announce an opportunity for a highly motivated postdoc in the field of Wireless Communication and Sensing. If you're passionate about pushing the boundaries of technology, this is your chance to make a significant impact in areas such as: - Physical layer optimization - Signal...
-
Phd Position Data-efficient Machine Learning for
2 maanden geleden
Delft, Nederland TU Delft VoltijdPhD Position Data-Efficient Machine Learning for Context-Sensitive Affective Computing- **_Challenge: Explore context-sensitivity of affect detection and data-efficient algorithms addresssing it._** **_ Impact: Increased performance and robustness in real-world settings (e.g. healthcare)._** Job description We seek a PhD student interested in working with...
-
Postdoc in Automated Inspection and Monitoring of
2 maanden geleden
Delft, Nederland TU Delft VoltijdPostdoc in Automated Inspection and Monitoring of Wind Turbine Blades in the AIRTuB-ROMI Project- **_Join the TU Delft team developing sensor technology to automate the inspection and monitoring of wind turbines to support the clean energy transition._** Job description Wind turbines play an important role in the future carbon-neutral society. To optimize...
-
Postdoc in Digital Twins for Energy Valleys
5 maanden geleden
Delft, Nederland TU Delft VoltijdPostdoc in Digital twins for Energy Valleys- Join us and start your carrier as a researcher and scientist in the field of power and energy systems. Develop digital twins for energy valleys and speed up energy transition at local scale. Job description This positions is a part of the REFORMERS Horizon EU project. The postdoc will collaborate with partners...
-
Phd Position Stochastic Safe Envelope Prediction of
2 maanden geleden
Delft, Nederland TU Delft VoltijdPhD Position Stochastic Safe Envelope Prediction of Damaged Drones- **_In this ERC Consolidator Grant project a new paradigm called Artificial Physical Awareness will be developed that aims to improve the efficiency and safety of autonomous robots after system failures._** Job description This PhD project is conducted within the ERC Consolidator Grant...
-
Postdoc in Scalable and Secure Ai in Data Lakes
2 maanden geleden
Delft, Nederland TU Delft VoltijdPostdoc in Scalable and Secure AI in Data Lakes- Job description Summary: We are searching for a motivated postdoctoral researcher to lead the research and development of dataset discovery and data cleaning, and privacy-preserving ML training and inference in data lakes. You will be working alongside a team of excellent PhD & MSc students, and taking part...
-
Postdoc Modelling of Aviation's Climate Impact for
5 maanden geleden
Delft, Nederland TU Delft VoltijdPostdoc Modelling of Aviation's Climate Impact for Eco-efficient Flight Trajectory- **_Challenge: Develop a climate model that enables climate optimized flight trajectories to be achieved at robust manner._** **_ Change: Improve the current climate model with broadening their geographical coverage and incorporating associated weather uncertainties._** **_...
-
PhD Decentralised Machine Learning Researcher
4 weken geleden
Delft, Zuid-Holland, Nederland Technische Universiteit Delft (TU Delft) VoltijdTransforming the Internet into a Global BrainWe are seeking a highly motivated PhD candidate to join our team at TU Delft's Tribler Lab, where we are working on a groundbreaking project to develop a fully decentralised video search engine. This innovative project aims to eliminate the need for servers in machine learning, harnessing the massive computing...
-
Postdoc in Near Wellbore Characterisation and
3 maanden geleden
Delft, Nederland TU Delft VoltijdPostdoc In Near Wellbore Characterisation and Architectural Element Modelling of Heterolithic Tidal Reservoir Zones- Job description The ’Near wellbore characterisation and architectural element modelling of heterolithic tidal reservoir zones’ project (REVFlow) aims to develop a faster method to determine the key differences of the flow and transport...
-
Postdoc in Automated Inspection of Wind Turbine
2 maanden geleden
Delft, Nederland TU Delft VoltijdPostdoc in Automated Inspection of Wind Turbine Blades in the NXTGEN Project- **_Join the TU Delft team developing sensor technology to automate the inspection and monitoring of wind turbines to support the clean energy transition._** Job description Wind turbines play an important role in the future carbon-neutral society. To optimize the energy output...
-
Postdoc Bio-inspired Safe Envelope Sensing and
2 maanden geleden
Delft, Nederland TU Delft VoltijdPostdoc Bio-inspired Safe Envelope Sensing and Upset Recovery- **_In this NWO Vidi project new controllers will be developed for damaged drones that can balance safety and performance based on computed and forecasted safe envelope boundaries._** Job description **Requirements**: **Need-to-haves** Excellent knowledge of the following fields: - Nonlinear...
-
Phd Position Machine Learning for Human Behaviors
2 maanden geleden
Delft, Nederland TU Delft VoltijdPhD position Machine learning for Human Behaviors in Negotiations and Deliberations- Job description Negotiations and deliberations involve understanding and managing interpersonal dynamics, relationships, motivations, and navigating conflicts. While there has been much existing research in building negotiating agents, there remains a gap to integrate...
-
Postdoc Research Corrosion of Light-alloys for
2 maanden geleden
Delft, Nederland TU Delft VoltijdPostdoc Research Corrosion of Light-alloys for Commercial Nuclear Reactors Applications- Job description Research reactors (RRs) comprise various civil and commercial nuclear reactors. Although they are not used for power production, they play a crucial role in the development of nuclear science and technology. Substantial damage to the material’s...
-
Postdoc Improved Electron Microscopy of
3 maanden geleden
Delft, Nederland TU Delft VoltijdPostdoc Improved Electron Microscopy of Increasingly Small Semiconductors- **_Challenge_**_: Nanoscale imaging of next-gen semiconductor chips._ **_ Impact_**_: Faster and more reliable electron imaging for the semicon industry._ Job description **The goal of this Postdoc is on **Signal generation and detection**: How to measure, understand and mitigate...
Postdoc Federated Learning for Autonomous Vehicle Perception and Prediction
3 maanden geleden
Autonomous vehicles have come a long way from initial public testing with safety drivers to fully driverless deployments in multiple cities across the world. However, to further improve these vehicles, they need to be trained from ever growing data sources collected by their fleets. Due to the vast cost of storing and processing this data, car manufacturers face the problem that they can only store a fraction of it (storing 1h of data costs about $5000 per year). Therefore new paradigms are needed to reduce the storage and processing cost.
Federated learning is such a novel paradigm that revolutionizes how Machine Learning systems are trained. Rather than storing all data on a central server and training there, federated learning allows us to learn in a distributed way. In the case of autonomous vehicles, this means that every vehicle can perform training steps while the system is idle, thereby saving energy and bandwidth. Furthermore, federated learning is much less privacy-sensitive, since sensor data of faces does not need to be transferred to the cloud.
The Intelligent Vehicles section at TU Delft, the Netherlands, invites applications for a fully funded two-year (up to 30 months) Post-Doctoral research position in the area of federated learning for autonomous vehicles. This position is part of the EU Horizon project Cynergie4MIE and in collaboration with the chip company NXP. You will be one of the first to train modern perception and/or prediction (a.k.a. motion forecasting) algorithms in a federated learning setup and provide an analysis of the pros and cons of this approach. While the exact task (detection, segmentation, prediction) is flexible, it should make use of radar sensors, potentially fused with other sensors. Your results will be published in top tier conferences like CVPR, ICCV, ECCV, ICRA and NeurIPS. For your work you will have access to the compute resources of TU Delft, ranging from personal machines, to shared GPU servers, the Delft AI Cluster that is shared across departments, as well as DelftBlue, which is one of the top 250 supercomputers in the world. Your main supervisor will be Dr. Holger Caesar, creator of the nuScenes dataset and co-author of the PointPillars method for lidar-based object detection. You will receive hands-on mentoring for your career development and help with applying for future research grants, to kick-start your continued academic career.
Requirements
- We are seeking Post-Doc applicants with an interest in performing cutting edge research in an active and exciting research area.
- Prospective applicants should have a strong academic record with a solid background in sensor processing (vision/radar/lidar, sensor fusion) and Machine Learning (Deep Learning, optionally federated learning).
- Good programming skills (Python/Matlab) and knowledge of deep-learning frameworks (TensorFlow/PyTorch) are expected.
- A certain affinity towards turning complex concepts into real-world practice (i.e. vehicle demonstrator) is desired.
- The successful candidate is expected to be able to act independently as well as to collaborate effectively with members of a larger team and supervise Master and PhD students.
- Good English skills are required.
Conditions of employment
Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities. The TU Delft offers a customisable compensation package, discounts on health insurance, and a monthly work costs contribution. Flexible work schedules can be arranged.
From 1 September next, a salary increase of 3.7% applies due to a Collective Agreement amendment, followed by an additional 1% increase on 1 January 2025. In addition, most employees employed on 1 September 2024 will receive a one-off payment of €300 gross based on full-time employment.
For international applicants, TU Delft has the . This service provides information for new international employees to help you prepare the relocation and to settle in the Netherlands. The Coming to Delft Service offers a for partners and they organise events to expand your (social) network.
TU Delft (Delft University of Technology)
Delft University of Technology is built on strong foundations. As creators of the world-famous Dutch waterworks and pioneers in biotech, TU Delft is a top international university combining science, engineering and design. It delivers world class results in education, research and innovation to address challenges in the areas of energy, climate, mobility, health and digital society. For generations, our engineers have proven to be entrepreneurial problem-solvers, both in business and in a social context.
At TU Delft we embrace diversity as one of our core and we actively to be a university where you feel at home and can flourish. We value different perspectives and qualities. We believe this makes our work more innovative, the TU Delft community more vibrant and the world more just. Together, we imagine, invent and create solutions using technology to have a positive impact on a global scale. That is why we invite you to apply. Your application will receive fair consideration.
Challenge. Change. Impact
Faculty Mechanical Engineering
From chip to ship. From machine to human being. From idea to solution. Driven by a deep-rooted desire to understand our environment and discover its underlying mechanisms, research and education at the ME faculty focusses on fundamental understanding, design, production including application and product improvement, materials, processes and (mechanical) systems.
ME is a dynamic and innovative faculty with high-tech lab facilities and international reach. It’s a large faculty but also versatile, so we can often make unique connections by combining different disciplines. This is reflected in ME’s outstanding, state-of-the-art education, which trains students to become responsible and socially engaged engineers and scientists. We translate our knowledge and insights into solutions to societal issues, contributing to a sustainable society and to the development of prosperity and well-being. That is what unites us in pioneering research, inspiring education and (inter)national cooperation.
Click to go to the website of the Faculty of Mechanical Engineering. Do you want to experience working at our faculty? These will introduce you to some of our researchers and their work.
