Robotic Foundation Model Engineer Intern (Human)
- Metzingen, Germany +1
- On-site
- Internship
- Intern/New Grad
- Master's degree
- Posted
Skills
Required
- Robotics
- PEFT / LoRA
- evaluation
- Electrical Engineering
- full fine-tunes
- dataset curation
- distillation
- VLA
- policy-learning
- π0 / π0.5
- OpenVLA
- LeRobot
- Python
- C++
- PyTorch / TensorFlow
Preferred
- machine-learning
- vision-based manipulation / reinforcement/imitation learning / multimodal models
- AWS / Azure / GCP
- robotic simulation tools
- IsaacSim
- MuJoCo
- NeuraGym
- teleoperation
- data annotation
- data mixture
Drive the development of cognitive robotics applications through Physical AI and the NeuraGym platform.
Responsibilities
- Training & Fine-tuning cutting-edge models: Take foundation models to production-ready robotic intelligence by executing the full NeuraGym pipeline — including teleoperation, data annotation, training, simulation, deployment, and validation — tailored to real-world robotics applications. Define the data strategy that makes a fine-tune work and own the full post-training loop inlcuding hyperparamter interation, data mixture, LoRA and a honest evaluation.
- Hands-on robotics: Collaborate closely with multidisciplinary engineering teams to design, build, and optimize next-generation intelligent robotic systems powered by AI.
- Customer Enablement & Support: Guide and onboard users to NeuraGym by reviewing training pipelines and scripts, identifying data quality issues, troubleshooting model behavior, and providing hands-on support to resolve persistent blockers.
- Cross-Functional Collaboration: Serve as a key interface between the Cloud and AI teams, ensuring smooth collaboration, technical alignment, and efficient problem-solving across domains.
- Product & Research Feedback Loop: Translate field experience and customer insights into actionable feedback for both the NeuraGym product roadmap and the Neura core AI roadmap
- What we can look forward to
Requirements
- Master’s degree in Computer Science, Robotics, Electrical Engineering or related field
- Demonstrable experience fine-tuning large pretrained models for robotics or another domain: PEFT/LoRA and full fine-tunes, dataset curation, distillation, and evaluation. Familiarity with the open VLA and policy-learning ecosystem (e.g. π0/π0.5, OpenVLA, LeRobot, diffusion policies) is a strong plus
- Solid Python skills (C++ a plus); practical experience with PyTorch or TensorFlow
- Comfortable working directly with real robot hardware and associated middleware
- Proven problem-solving abilities and ability to handle multiple projects in parallel
- Strong bias toward execution and a high level of personal commitment: you take deployments personally, work through setbacks, and measure yourself by what runs at the customer
Preferred
- Hands-on machine-learning experience in robotics - strong in at least one of: vision-based manipulation, reinforcement/imitation learning, or multimodal models - and keen to learn the rest
- Cloud experience (AWS, Azure, or GCP) and experience with robotic simulation tools (IsaacSim, MuJoCo, etc.) is a plus
Clear communicator who can translate between researchers, engineers and end-users. You have a good command of English and German language (B2 - C1 level)
