Physical AI Padawan Wanted (mfd) – Robotics Internship | Munich
Job Summary
Now were scaling it into reality and we need the next generation of physical AI talents who can make the impossiblereliable.
Atsewts we build the intelligence that lets robots manipulate deformable materials like textiles towels cables with human-like precision. Our systems are already deployed in production across Europe and expanding into the US.
We are building a foundational technology stack called. JUPITER usesgenAIto simulate realistically the behaviour of deformable & soft objects to create corresponding computer vision models and grabbing strategies. Based on our physicalAIfirst time ever robots are enabled to handle soft & deformable materials. With over 10M in funding we will bring automation into all untapped industries like cloth manufacturing textiles handling recycling & e-commerce.
This is where AI leaves the screen and enters the physical world.
And in the physical world nothing forgives you.
Your Mission
You make Physical AIwork in reality.
YouwillworkdirectlywithengineersbuildingAIsystemsfordeployedroboticsproductsandcontributetotechnologythatoperatesoutsidethelab.Youlearnfastbuildfast andsolveproblemsmostpeopleavoid.Gripping of deformable materials like textiles is a task most humans see as intuitive and simple. However this is a complicated task for robots as they lack the detailed and contextual understanding of where and with what level of sensitivity to handle these textiles.
WhatYoullActually Do
- Support building and scalingAI systems that run on real robots in real environments;
- Contribute to the development of deep learning models (PythonPyTorch) for computer vision and manipulation;
- Collaborate on design and maintain end-to-end ML pipelines (training evaluation deployment);
- Own experiment tracking reproducibility and model lifecycle discipline;
- Push model performance toward robustness under real-world noise and edge cases;
- Automate training workflows hyperparameter optimization and model iteration loops;
- Work tightly with roboticsMLOps and simulation teams;
- Help shapeinto a production-grade Physical AI platform.
- One of a kind student with roots incomputer vision computer science informatics robotics or equivalent;
- Strong Python PyTorchfundamentals;
- Excited about model training evaluation and failure modes;
- Experience with ML pipelines cloud infrastructure orMLOpstooling;
- You care about what survives contact with reality not just what looks good in experiments;
- You move fast think clearly and fix things when they break;
- Youre comfortable operating without perfect structure;
- Youre fluent in English.
- Experience with robotics industrial AI or embodied systems;
- Vision Language Models or scene understanding exposure;
- Model optimisation (TensorRT quantisation PTQ);
- Experience inproductionizingmachinelearningsolutions.
- You build AI that physically acts in the worldnot just predicts it;
- Your work runs directly on deployed robotic systems;
- Small team extreme ownership no abstraction layers;
- You shape a category: Physical AI for deformable materials;
- Real impact is visible in production not dashboards;
- Munich-based high-performance environment.
- Competitive salary;
- SpecialityCoffee at office;
- Flexible working setup;
- Regular Team events high trust low bureaucracy.
Things will break. Edge cases will win.
If you want clean problems this is not it. If you want to build intelligence thatsurvivesthe real worldwelcome tosewts.
You may use the following channels to connect with her:
Email:
WhatsApp:
Required Experience:
Intern
About Company
At sewts we are automating complex processes by teaching robots human-like perception skills. We are a young, ambitious, and diverse team of eight different nationalities with the mission to become the global go-to Partner for automated processing of deformable and soft materials. We ... View more