Senior AI Engineer Self-Supervised Learning

Senior AI Engineer Self‑Supervised Learning

Join RIVR, a Swiss robotics company pioneering Physical AI and robotic solutions to revolutionize last‑mile delivery, offering the power of 1000 robots to one human. Combining artificial neural networks with innovative robot designs, RIVR improves efficiency, sustainability, and scalability in delivery operations. Founded as Swiss‑Mile and rebranded in 2025, the company leads in translating AI and robotics into real‑world applications with strong ties to ETH Zurich.

RIVR is committed to building a diverse and inclusive team that values every perspective. If you’re passionate about driving innovation in robotics and creating meaningful impact, we encourage you to apply.

Our global fleet of autonomous robots generates vast amounts of multi‑modal sensor data. While our VLA team builds large‑scale models, much of this data remains unlabeled and unstructured. We need an expert in self‑supervised and representation learning to unlock this potential.

In this role, you will design and build the core data engine that transforms raw, real‑world sensor data into high‑signal, structured datasets for neural‑network training. You will pioneer methods to automatically curate, filter, and pseudo‑label data, creating powerful representations for downstream tasks such as navigation, imitation learning, and decision‑making. You will work directly with the VLA and RL teams to define data strategies and interfaces, ensuring the data you produce accelerates their model development.

• Design, build, and maintain scalable data pipelines to process, filter, and transform terabytes of raw, multi‑modal sensor data (e.g., video, LiDAR, IMU, odometry) from our robotic fleet.
• Develop and implement state‑of‑the‑art self‑supervised and representation learning algorithms to automatically extract features, discover patterns, and generate pseudo‑labels from unlabeled data.
• Collaborate closely with the VLA Foundation Model and RL teams to define data requirements, APIs, and strategies for leveraging curated datasets and learned representations.
• Architect and implement robust evaluation strategies, benchmarks, and datasets to rigorously track the performance and quality of both the data pipeline and the downstream models that consume it.
• Own the data integration workflow, creating efficient data loaders and access patterns to make high‑signal data readily available for model training and experimentation.
• Research and prototype novel techniques in data curation, active learning, and anomaly detection to continuously improve the quality and efficiency of our data engine.

• Master’s degree or higher in a relevant field such as Computer Science, Machine Learning, or Robotics.
  
  • 3+ years of industry or research experience (PhD experience is applicable).
• Deep expertise in self‑supervised learning (SSL) and representation learning, particularly with multi‑modal sensor data (e.g., contrastive learning, masked autoencoders, world models).
• Proven experience building and managing large‑scale data processing pipelines for machine learning (e.g., Spark, Kubeflow, or similar cloud‑native tools).
• Strong understanding of robotic sensor data (e.g., camera, LiDAR, IMU, odometry) and their characteristics.
• Strong programming skills in Python and deep experience with PyTorch, including creating custom and efficient Data Loaders.
• Experience with MLOps best practices and data versioning tools (e.g., DVC, Pachyderm).

• PhD degree in Robotics, Engineering, Computer Science, Machine Learning, or a similar discipline, or equivalent research experience.
• Publications at top‑tier ML or robotics conferences (e.g., NeurIPS, ICML, CVPR, CoRL, ICLR).
• Experience with generative models (e.g., GANs, Diffusion Models) for data augmentation or simulation.

RIVR is committed to building a diverse and inclusive team that values every perspective. If you’re passionate about driving innovation in robotics and creating meaningful impact, we encourage you to apply and bring your unique self to our team.

We believe the best work is done when collaborating and therefore require in‑person presence in our office locations.

Referrals increase your chances of interviewing at RIVR by 2x.