The Role
As a Reinforcement Learning intern, you will advance robotic navigation capabilities by developing ML models and tools under guidance from experts.
Summary Generated by Built In
ANYbotics is a fast-growing tech company dedicated to shaping the future of mobile robotics across multiple industries. Join our highly talented and motivated team of more than 190 people and work on cutting-edge robot technology.
The Opportunity
We are looking for a Reinforcement Learning for Robotic Navigation intern to join our Navigation team and contribute to advancing ANYmal's mobility capabilities. Utilizing the latest reinforcement learning techniques and simulation tools, we define, train, and integrate ML models into ANYmal to safely and robustly navigate challenging industrial environments.
Your role extends to designing and implementing essential processes, pipelines, and tools for all stages of the RL lifecycle, ensuring seamless training, evaluation, and deployment of our learning-based controllers. This internship provides a profound and impactful opportunity to work at the forefront of machine learning in robotics, playing a significant role in shaping ANYmal's autonomous capabilities and contributing to real-world applications.
You will work closely with Robotics experts who will provide you with guidance and mentorship. The preferred starting date is October, and the full-time paid internship lasts six months.
Market & Our Technology
ANYbotics transforms industrial plants in the energy, process, and utility sector by introducing robotics to a wide range of novel applications that so far were beyond reach. Our customers are large asset operators and industrial service providers pioneering the use of robotics technology for inspection and maintenance. Our mobile robot ANYmal uses legs for extreme mobility in complex environments, camera- and LIDAR-based sensing for full autonomy and obstacle avoidance, and AI for high-quality and consistent inspection results. We develop numerous customized hardware systems, including the entire robotic platform, actuators, sensors, inspection payloads, charging systems, and all related ANYbotics mechanical hardware.
Your Contributions
- Robustify ANYmal’s local obstacle avoidance capabilities using state-of-the-art RL methods
- Investigate various neural network architectures and conduct comparative performance analyses
- Develop and expand tools for explainable artificial intelligence
- Collaborate with Navigation experts on improving the reliability and scalability of ANYmal’s navigation stack
Your Profile
- Currently a master's, PhD student or recent graduate in computer science, machine learning, robotics, or related fields
- Experience in Reinforcement Learning, mainly if applied to solving navigation problems in either robots or autonomous driving
- Proficiency in Python and familiarity with ML frameworks such as PyTorch and/or Tensorflow
- Experience with physical simulators, such as Isaac Sim/Gym, Mujoco, Pybullet, etc.
- Goal-oriented mindset with a proactive approach to achieving objectives
- Proficient in English
- Experience in training and deploying navigation policies on real robots.
- Experience with C++
Bonus
Please note that we are only able to consider applications from Students enrolled in a Swiss University who reside in Switzerland.
We offer you a very exciting and dynamic work environment, the opportunity to become part of a fast-growing company and an ambitious team that is on a mission to change the industrial inspection market, a chance to leverage your experience and bring in your own ideas, a fair market salary, an attractive employee stock ownership plan, and a job in the city of Zurich.
Top Skills
C++
Gym
Isaac Sim
Mujoco
Pybullet
Python
PyTorch
TensorFlow
Am I A Good Fit?
Get Personalized Job Insights.
Our AI-powered fit analysis compares your resume with a job listing so you know if your skills & experience align.
Success! Refresh the page to see how your skills align with this role.
The Company
What We Do
ANYbotics is a Swiss robotics company pioneering the development of autonomous mobile robotics. Our walking robots move beyond conventional, purpose-built environments and solve customer problems in challenging infrastructure so far only accessible to humans. Founded in 2016 as a spin-off from the world-leading robotics labs at ETH Zurich. Join our highly talented and motivated team of more than 100 people and work on cutting-edge robot technology. Our customers include leading international energy, industrial processing, and construction companies. In 2020, ANYbotics raised CHF 20 m in a Series A financing round and won several prizes, including the Swiss Economic Forum 2020 award.
