Metric Geo
AI Engineer - Motion Generation for Robotics
Metric GeoSwitzerland12 days ago
Full-timeResearch, Engineering

Role Overview

We are seeking an AI Engineer with deep expertise in generative modelling—particularly diffusion models and flow matching—to build next-generation multi-modal systems for robotic motion and trajectory generation. This role is ideal for researchers with a strong foundation in human modelling and perception, especially those eager to translate that expertise into real-world robotics. You will design and deploy models that help robots understand, predict, and respond to human behaviour, enabling more intelligent and adaptive motion generation. Working closely with robotics, simulation, and AI teams, you will bring advanced generative and human-centred modelling techniques from research into high-performance, on-hardware applications.


Responsibilities

  • Develop and optimise diffusion and flow matching models for robotic trajectory and motion generation.
  • Build multi-modal generative pipelines integrating robot state, perception, and intent signals.
  • Train and fine-tune large generative models in PyTorch for high-fidelity motion synthesis.
  • Deploy trajectory-generation models onto real robotic systems, ensuring robust on-hardware performance.
  • Leverage modern GPU-based simulation tools (e.g., Omniverse, Genesis) for data generation and model evaluation.
  • Collaborate with cross-functional teams to integrate generative models into full-stack robot systems.
  • Maintain documentation, perform code reviews, and support debugging during deployment cycles.


Qualifications

  • PhD or Master’s degree in diffusion models, flow matching, motion generation, or a closely related field, with strong research or project work.
  • Excellent proficiency in Python, PyTorch, and modern deep learning workflows.
  • Hands-on experience training and deploying diffusion or flow matching models.
  • Prior experience applying generative models to robotics, motion planning, or trajectory optimisation – in simulation environments or on physical hardware
  • Familiarity with GPU-based simulation environments (Omniverse, Genesis, or equivalents).
  • Strong knowledge of modern machine learning architectures and training techniques.


Benefits

  • Opportunity to join a fast-moving, early-stage robotics team where every engineer has meaningful ownership and impact.
  • Work on cutting-edge humanoid and manipulation technologies with significant technical depth.
  • Dynamic, collaborative environment with quick iteration cycles and high autonomy.
  • Competitive compensation package, including base salary and role-dependent benefits.


If you’re excited about advancing generative models for real robotic motion, we’d love to hear from you.

Key Skills

Ranked by relevance