Postdoctoral Fellowship (17) at ETH Zurich, Switzerland

The postdoc will develop and implement cutting-edge machine learning approaches for automated trait estimation, focusing on:

• Foundation Models for Phenotyping: Leveraging and adapting pre-trained foundation models for crop trait estimation in both pure stands and crop mixtures, minimising computational and data annotation overheads while maximising generalisation power
• Domain Transfer Methods: Developing plant-aware image-based domain transfer techniques to enable models trained on high-resolution FIP images to work effectively with lean device images (e.g., smartphone cameras)
• 3D Reconstruction and Rendering: Creating 3D point clouds from multi-view setups and rendering realistic 2D images across different viewpoints, leveraging among many approaches generative models, neural rendering and implicit models
• Human-in-the-Loop Approaches: Implementing active learning strategies that incorporate expert feedback at inference time, enabling real-time model correction and improvement with minimal labelling budget
• Field Evaluation: Conducting rigorous qualitative and quantitative evaluations of developed models on farm field experiments, integrating expert feedback to improve model performance
• Data Product Generation: Preparing comprehensive time series datasets of derived products, including raw data, 3D reconstructions, model estimations, and reference measurements for downstream analyses
• Software Development: Developing and maintaining codebases for the implemented methods, ensuring reproducibility, and facilitating future research and applications in the field of plant phenotyping

The introduction of fiber optics in the 1970s has revolutionized the telecommunications industry upon the replacement of copper wires and played a major role in the advent of the Information Age – One high bandwidth fiber optic cable can replace thousands of electrical links to transmit the same amount of information. As a parallel to the thriving fields of soft devices and robots controlled by electrical signals, soft optics is emerging as a new platform that uses the modulation of light in soft matter to encode multifunctionalities in the optical path. 

The focus of this project is to expand both actuation and sensing capacities with light. The project will create an artificial sensorimotor network with densely distributed actuators and sensors similar to the biological neuromasculature. The first part of the project will develop a single soft optical fiber with distributed multimodal actuators that are also self-sensing. The second part will study grouped behavior of these “muscle bundles” to enable muscle coordination for complex/adaptive/efficient movements.

The introduction of fiber optics in the 1970s has revolutionized the telecommunications industry upon the replacement of copper wires and played a major role in the advent of the Information Age – One high bandwidth fiber optic cable can replace thousands of electrical links to transmit the same amount of information. As a parallel to the thriving fields of soft devices and robots controlled by electrical signals, soft optics is emerging as a new platform that uses the modulation of light in soft matter to encode multifunctionalities in the optical path. 

The focus of this project is to create biocompatible, high performance soft actuators multiplexed by light, all integrated on a miniature fiber, delivering advanced robotic and biomedical functions as minimally invasive surgical tools and implantable devices.

• We are seeking physical climate scientists with research experience in studying weather and climate extremes using coupled global and Earth System Models, regional climate and convection-permitting models, or AI weather models or in using process-based or statistical analysis of model results and reanalyses
• The applicant is expected to contribute to NCCR CLIM+ and to take leadership in the research field, including the supervision of students
• The position is for two years initially and can be extended subject to performance and availability of funding
• The starting date is as soon as possible but can be negotiated

• Plan, conduct and analyse hydraulic stimulation experiments including proppant in vertical and horizontal boreholes (30–120 m scale) to investigate proppant transport, placement efficiency, and interaction with natural fracture networks
• Assess the effectiveness of different stimulation strategies and proppant placement approaches under varying geological conditions in terms of permeability enhancement and fracture geometry
• Collaborate with project partners performing small-scale laboratory experiments (GFZ) regarding joint interpretations and recommendations for the design full-scale hydraulic stimulation operations (e.g., Litoměřice site and other European contexts)
• Contribute to project deliverables and reporting, publish results in peer-reviewed journals and present findings at international conferences
• Collaborate closely with project UPLIFT partners (GFZ, various industry partners) and support coordination between experimental, modelling, and field activities

The position takes place within the recently awarded Meta.Morphos project, funded by the ESA ESDI Phi-Lab Switzerland. The overarching goal of the project is to develop methods to design and produce thermally actuated structures and mechanisms incorporating thermo-electric materials. Such devices have interesting applications in space under significant weight, volumetric, power, and resource constraints.

The project consortium includes multiple labs at ETH Zurich and research partners at Inspire AG, as well as industrialization partners. The main focus of this position will be to develop materials and methods for directly depositing and fabricating thermo-electric devices onto non-planar metallic substrates. In a parallel track, the team will develop techniques for the design and manufacture of the structures with predictable material properties. Finally, the two technologies will be combined to create integrated devices. The industrial partners will provide application-specific use cases, environmental testing expertise and facilities, and validation.

The successful candidate will lead GNSS-based research within our group and support existing projects related to GNSS and PNT. Key responsibilities include:

• Software Development: Developing GNSS software using Factor Graph Optimization (FGO) based on existing open-source software packages 
• Sensor Fusion: Implementing multi-sensor fusion strategies
• Resilience: Advancing real-time GNSS processing with a primary focus on the detection, characterization, and mitigation of jamming and spoofing scenarios 
• AI Integration: Exploring the integration of AI/ML concepts to enhance navigation resilience together with other group members 
• Hardware & Simulation: Working with both high-grade and low-cost GNSS equipment and utilizing a GNSS signal simulator (Spirent) 
• Academic Leadership: Leading and co-authoring high-impact publications and participating in the preparation of grant applications
• Teaching & Supervision: Supporting the lectures “GNSS” and “Navigation” (full course materials exist) and contributing to the supervision of PhD and Master students

• Collaborate with other researchers to develop high-fidelity emulators for large-scale, energy system optimization models
• Lead the design and implementation of innovative methods, which could include but are not limited to: Kriging surrogate, Polynomial Chaos Expansion (PCE), and Physics-Informed Neural Networks (PINNs)
• Contribute to the strategic direction of research
• Publish high-impact research in leading journals and present findings at international conferences on energy systems and machine learning
• Collaborate with industry partner to tackle challenges of practical relevance