PhD / Postdoc Positions in AI & Robotics

Description

We are hiring multiple talented PhD and Postdocs in AI! Be part of where breakthroughs really happen!

We are seeking highly motivated PhD students and postdoctoral researchers to join our lab and make a significant impact on real-world challenges!

Our researchers have earned numerous prestigious awards, and our alumni have gone on to lead teams at top-tier companies, become professors, and establish successful startups.

Our work has received global recognition, with coverage in The Guardian, The New York Times, Forbes, The Economist, and BBC, highlighting achievements such as outperforming world champion drone racing pilots and advancing high-speed navigation with event cameras.

If you're passionate about advancing research, technology, and innovation, apply now to join a team that is shaping the future.

The mission of the Robotics and Perception Group is to research the fundamental challenges of robotics and computer vision that will benefit all of humanity, and we want people with diverse perspectives and backgrounds. Our team includes various nationalities, genders, and ages.

We have several fully-funded positions for PhD students and PostDocs in:

• Space Navigation and Landing with Event-based Cameras
• Vision-based Robot Learning with Foundation Models
• Low-Energy Vision with Event Cameras

Check here for further info on:

• Starting Date
• Benefits of working with us
• Who we are
• Your skills

HOW TO APPLY

Important Deadline for Applications and Starting Date

There is no closing deadline but the early you apply the better: we have already started the screening of applications and will continue until the positions are filled. Thus, we encourage you to apply asap if you want to be guaranteed a spot.

Starting date: as soon as possible.

Space Navigation and Landing with Event-based Cameras

Seeing in space is nothing like seeing on Earth. Extreme lighting variations, rapid motion, and deep shadows challenge traditional cameras, causing motion blur, limited dynamic range, and limitations in latency and bandwidth. Event-based cameras offer an alternative with very high dynamic range (around 120dB), microsecond latency, and milliwatt power consumption. However, since they do not provide absolute intensity information, robust real-world systems typically require fusion with standard frame-based cameras (and often inertial sensors).

The goal of this PhD is to develop computationally efficient, low-power methods to combine event and frame data on space-qualified hardware , while ensuring low-latency and energy-efficient processing. The core focus will be tracking , as it is fundamental to many space tasks, with visual odometry (VO) as one of its most critical applications. By improving tracking, this work aims to enhance VO systems for: planetary landing (Entry, Descent, and Landing), real-time monitoring for space situational awareness , and motion estimation for rendezvous and docking , all within the strict computational and power constraints of space systems.

This PhD will be carried out in collaboration with ESA 's ZTH Robotics at ESTEC , leveraging the GRALS testbed to benchmark our system under realistic space-like conditions. Additionally, we will work with Thales Alenia Space , drawing on their expertise in deploying space-qualified solutions (e.g., ESA's VISNAVMars, where quasi-real-time (10Hz) Guidance, Navigation, and Control was demonstrated on low-power space-grade hardware for Entry, Descent, and Landing). Thales will provide real-world use cases, particularly in landing and rendezvous, and contribute expertise in synthetic image modeling tools for controlled testing.

If you want to know more about our research in this area, check out our page on event cameras and these papers:

• Data-driven Feature Tracking for Event Cameras : PDF , YouTube
• Ultimate SLAM? Combining Events, Images, and IMU for Robust Visual SLAM in HDR and High-Speed Scenarios : PDF , YouTube
• Low Latency Automotive Vision with Event Cameras : PDF , YouTube

Vision-based Robot Learning with Foundation Models

Navigating complex unstructured environments requires a deep understanding of the robot's surroundings. Where is it safe to navigate? What actions are too risky to take? How can the robot quickly adapt from experience collected during operation? To answer these questions, novel algorithms that combine machine learning, control, and vision are required.

Autonomous navigation based on onboard sensors and computation has made tremendous progress over the last decade (e.g., NASA Mars helicopter, Tesla autopilot, Boston Dynamics Atlas). However, the performance of these systems is still far from humans in of agility, versatility, and robustness: "agility" will allow the robot to increase its productivity, "versatility" to adapt to new environments and continually learn from new data, and "robustness" to succeed at any task.

The goal of the PhD will be to research deep learning algorithms (imitation learning, reinforcement learning, differentiable simulation) with foundation models to train sensorimotor policies that can navigate robots better than humans, end to end, by mapping visual inputs to control commands. Experimental platforms range from flying robots to legged robots and cars. Your research will revolve around learning from data collected online, learning from offline data (e.g., YouTube videos), and generalist, multi-task learning (learning behaviors that generalize to multiple tasks and scenarios). The specific topic will be decided with your PhD advisor, Prof. Davide Scaramuzza.

If you want to know more about our current research in this area, check out these papers for more details:

• Learning Quadruped Locomotion Using Differentiable Simulation : PDF
• Champion-level Drone Racing using Deep Reinforcement Learning ( published in Nature and featured on the cover ): PDF , YouTube
• Learning High-Speed Flight in the Wild : PDF , YouTube
• Deep Drone Acrobatics : PDF , YouTube
• Learning Minimum-Time Flight in Cluttered Environments : PDF , YouTube
• A Benchmark Comparison of Learned Control Policies for Agile Quadrotor Flight : PDF , YouTube

Also, check out our related research pages:

• Our general research on autonomous drones
• Our research on drone racing
• Our research on agile flight

This PhD will be done within the EU projets AGILEFLIGHT and AUTOASSESS .

Low-Energy Vision with Event Cameras

The goal of this PhD is to fuse event cameras with standard cameras and inertial sensors to improve the energy consumption and latency of future computer vision algorithms (SLAM and/or object tracking) for autonomous vehicles and mobile devices (e.g., AR/VR). Event cameras are bio-inspired vision sensors that output pixel-level brightness changes instead of standard intensity frames. They offer significant advantages over standard cameras, namely a very High Dynamic Range (HDR), no motion blur, latency with microsecond resolution, and low bandwidth. However, because the output is asynchronous, traditional vision algorithms cannot be applied, and new algorithms must be developed to take advantage of them.

If you are interested to know more about our current research in this area, check out our related research page on event cameras .

Also, check out these papers for more details:

• Low Latency Automotive Vision with Event Cameras : PDF , YouTube
• Data-driven Feature Tracking for Event Cameras : PDF , YouTube
• TimeLens: Event-based Video Frame Interpolation : PDF , YouTube
• Ultimate SLAM? Combining Events, Images, and IMU for Robust Visual SLAM in HDR and High-Speed Scenarios : PDF , YouTube
• Dynamic Obstacle Avoidance for Quadrotors with Event Cameras : PDF , YouTube

This PhD will be done within the EU projets AGILEFLIGHT and AUTOASSESS .

Benefits of working with us

• We do world-class research: our two recent papers were published in Nature: PDF , YouTube , PDF , YouTube
• We were the first to demonstrate an AI beating the best human in a physical world (previous AI wins in chess, Dota, Starcraft, Gran Turismo, and Go were done in simulation or board games): PDF , YouTube .
• Our students and postdocs have won many international awards and paper awards; check out the full list here .
• Whatever you will do with us, you will do well: all our former students and postdocs have landed at great companies or universities (MIT, Berkeley, Google, Facebook, Microsoft, Skydio)
• Our research is often featured in the world news (The Guardian, The New York Times, Forbes, The Economist, BBC, etc.). Full list here .
• The position is fully funded and is a regular job with social benefits (e.g., a pension plan, accident insurance) .
• You will get a very competitive salary and access to world-class research facilities ( one of the world's largest motion capture arenas , 3D printing, electronic and machine workshops, world-class GPU infrastructure.
• Excellent work atmosphere with many social events, such as ski trips, hikes, lab dinners, and lab retreats ( check out our photo gallery ).
• Regular visits and talks by international researchers from renowned research labs or companies.
• Collaboration with other top researchers in both Switzerland and abroad.
• Zurich is regularly ranked in the top cities in the world for quality of life ( link ).
• Switzerland is considered the Silicon Valley of Robotics (link) .
• Robotics papers from Switzerland each year collect the highest number of citations (normalized by country's populatio