AI Engineer - VLA model, RIVR

RIVR Technologies AG; Zürich; On-site; CHF 180,000 - 240,000; Full time

Job summary

RIVR Technologies AG is seeking an expert in Vision-Language-Action models to lead multi-modal robotics research in Zürich. You will develop VLA models, imitation learning and transformer-based architectures to advance autonomous delivery robots in real-world environments.

You will supervise and mentor a team of software engineers, collaborate with RL teams, and help translate research into deployed edge solutions on hardware like Nvidia Jetson Thor.

Qualifications

• Minimum 3 years industry or research experience; PhD experience applicable.
• Strong deep learning fundamentals including supervised/self-supervised learning, Transformer-based architectures, policy optimization algorithms, imitation learning, and generative AI techniques (including Diffusion Models).
• Proven experience in developing Vision-Language-Action models or large-scale generalist robot models (e.g., RT-2, Octo).
• Strong background in robotics including autonomy, navigation.
• Experience with deploying artificial neural networks on hardware platforms.
• Ability to prototype algorithms and train deep neural networks in Python (Pytorch).
• Master’s degree or higher in a relevant field such as Engineering, Robotics, or Machine Learning.

Responsibilities

• Develop and implement Vision-Language-Action (VLA) models, generalist robot transformers, and imitation learning algorithms to enable robots to autonomously execute complex tasks.
• Design, test, and refine your algorithms to meet the demands of complex real-world autonomy and navigation tasks, with a focus on spatial reasoning and generalization.
• Streamline the data collection and training workflow to efficiently expand model capabilities with new tasks and data sources.
• Collaborate with the reinforcement learning team to innovate methods that leverage both simulated and real-world data.
• Optimize and distill networks for real-time deployment on the edge (e.g. Nvidia Jetson Thor).
• Build, lead and mentor an exceptional team of software engineers.
• Provide expert guidance to product managers and executives for strategic decision-making.
• Create and maintain documentation, guidelines, and best practices to streamline knowledge sharing.

Skills

Vision-Language-Action models

Imitation learning

Transformer-based architectures

Self-supervised learning

Generative AI

Python (PyTorch)

Edge deployment / embedded systems

Team leadership

Education

Master's degree or higher in Engineering/Robotics/ML

PhD preferred

Tools

PyTorch

C++

Job description

RIVR, an Amazon company, is building Physical AI by deploying autonomous robots for real-world doorstep delivery. Operating daily in diverse urban environments, RIVR's robots continuously learn from and navigate the millions of scenarios encountered during deliveries. By owning the full stack from software.

Our fleet of delivery robots operates globally today, generating vast amounts of robotic real-world data. By utilizing state-of-the-art Vision-Language-Action (VLA) models, large-scale generalist models (like Transformers), generative AI, and similar methods, we can leverage this pool of data to significantly enhance its autonomy, navigation, and manipulation skills. In this role, you will develop multi-modal models that enable robots to autonomously generate actions from demonstrations, real-time sensor data, and natural language commands. We are seeking an expert in VLA models, imitation learning, and generative AI techniques with a deep knowledge of supervised, and self-supervised learning algorithms. If you are passionate about pushing the boundaries of AI we invite you to join us in shaping the future of intelligent robotics.

Key job responsibilities

• Develop and implement Vision-Language-Action (VLA) models, generalist robot transformers, and imitation learning algorithms (e.g., diffusion policies) to enable robots to autonomously execute complex tasks.
• Design, test, and refine your algorithms to meet the demands of complex real-world autonomy and navigation tasks, with a focus on spatial reasoning and generalization.
• Streamline the data collection and training workflow to efficiently expand model capabilities with new tasks and data sources.
• Collaborate with the reinforcement learning team to innovate methods that leverage both simulated and real-world data.
• Optimize and distill networks for real-time deployment on the edge (e.g. Nvidia Jetson Thor).
• Build, lead and mentor an exceptional team of software engineers.
• Provide expert guidance to product managers and executives for strategic decision-making.
• Create and maintain documentation, guidelines, and best practices to streamline knowledge sharing.

BASIC QUALIFICATIONS

• At least three years of industry or research experience, with PhD experience applicable.
• Strong deep learning fundamentals including supervised learning, self-supervised learning, Transformer-based architectures, policy optimization algorithms, imitation learning, and generative AI techniques (including Diffusion Models).
• Proven experience in developing Vision-Language-Action models or large-scale generalist robot models (e.g., RT-2, Octo).
• Strong background in robotics including autonomy, navigation.
• Experience with deploying artificial neural networks on hardware platforms.
• Ability to prototype algorithms and train deep neural networks in Python (Pytorch).
• Master’s degree or higher in a relevant field such as Engineering, Robotics, or Machine Learning.

PREFERRED QUALIFICATIONS

• PhD degree in Robotics, Engineering, Computer Science, Machine Learning or a similar discipline, or an equivalent amount of research experience.
• Publications at top-tier conferences.
• Experience in managing a software team.
• Ability to write production-level code in modern C++