Internship / MS thesis – Robotics Engineer (VLM / VLA Models)

sensmore automates the world's largest machines with unprecedented intelligence. Our proprietary Physical AI enables heavy machines such as wheel loaders to instantly adapt to dynamic environments and execute new tasks without prior training.

We integrate cutting-edge robotics into a platform powering intelligence and automation products - transforming productivity and safety for customers in mining, construction, and adjacent industries today.

Join us and play a pivotal role in transforming the automation landscape in heavy industries.

Role Overview:

Key Responsibilities:

We are seeking a highly motivated Master’s student to join our team as an Intern specializing in General Purpose AI (GenAI), specifically Vision-Language Models (VLM) and Vision-Language-Action (VLA) models. This role is focused on the cutting edge of industrial automation: developing VLA systems that allow robots to navigate and interact within heavy industry environments. You will work on bridging the gap between multi-modal perception (video, radar, lidar) and physical execution, using state-of-the-art VLM/VLA frameworks to enhance robotic autonomy and reasoning.

Depending on your skill set and our current project needs, you will:

• Data Analysis & Engineering: Analyze and preprocess large-scale, multi-modal datasets including video, radar, and lidar streams.

• Dataset Generation: Work on self-supervised dataset generation pipelines to train next-generation VLA models.

• Model Development: Utilize state-of-the-art GenAI tools and frameworks (e.g., HuggingFace, Gemini, Unsloth) to build and refine models.

• Prompt & Model Optimization: Apply prompt optimization techniques and fine-tuning to improve model reasoning and action generation.

• Training & Evaluation: Execute training runs, monitor performance, and rigorously evaluate results using new industrial data.

• Deployment: Assist in optimizing model deployment to ensure reliability and real-time performance in production-grade heavy industry settings.

Required Qualifications:

• Current Enrollment: Strong academic standing in a Master’s program (Robotics, Computer Science, Electrical Engineering, Automation, or a related field).

• Technical Proficiency: Strong hands-on experience with Python and PyTorch.

• Ownership & Proactivity: Ability to take ownership of your tasks, ability to drive sub-projects from concept to execution with a "getting things done" mentality.

• GenAI Foundations: A deep interest in Vision-Language Models (VLM) and their application in Robotics and Automation.

• Project Experience: Initial successful projects or coursework in GenAI, Robotics, or Computer Vision.

Preferred Skills & Future Outlook:

• Frameworks: Familiarity with GenAI engineering tools such as HuggingFace, Gemini, and Unsloth.

• Optimization: Experience with prompt optimization techniques and model fine-tuning.

• Research: Previous machine learning research experience (e.g., publications, high-quality term papers, or a Bachelor’s thesis).

• Master’s Thesis: We highly value candidates who plan to write their Master’s Thesis in the field of Robotics and Automation.

• Long-term Perspective: We are looking for a collaborator who is interested in a long-term journey; a successful internship/working student period is intended to lead into a Master’s Thesis.

What We Offer:

• Build physical AI for the world's largest off-highway machinery – making them intelligent, safe, and ready for every tough task

• Join the pioneer in intelligent robotics backed by Point Nine & other Tier 1 investors

• Combine cutting-edge robotics research in end-to-end learning & Vision Language Action Model with real-world heavy mobile equipment

• Tailor your own career path, whether you like to become technical specialist or technical team lead

• Experience a great team culture, beverages, and an amazing office environment

Benefits:

• Attractive compensation package and stock options.

• Beverages on-site and regular social events.

• Engage with top-tier researchers, engineers, and thought leaders.

• Influence the future of robotic technologies and tackle significant technological challenges.

• Assistance with relocation to Berlin.

About Us:

Heavy machinery, light years ahead.

sensmore automates the world's largest machines with unprecedented intelligence. Our proprietary Physical AI enables heavy machines such as wheel loaders to instantly adapt to dynamic environments and execute new tasks without prior training.

We integrate cutting-edge robotics into a platform powering intelligence and automation products - transforming productivity and safety for customers in mining, construction, and adjacent industries today.

We are proudly backed by Point Nine and other Tier 1 investors.