AI Research Engineer: Dexterous Manipulation & VLA

Flexion Robotics; Zürich; Hybrid; CHF 120.000 - 180.000; Vollzeit

Benefits dieser Stelle

Competitive compensation

Enhanced pension plan

Paid holidays

Central Zürich office

Zusammenfassung

Flexion Robotics seeks an AI Research Engineer to lead dexterous manipulation and egocentric model development. You will build Vision‑Language‑Action models enabling humanoid robots to interact with the world with human‑like fluidity.

You’ll work in our Zürich office on state‑of‑the‑art learning‑based controllers, bridging video observations with high‑DOF robot policies for reliable, flexible manipulation.

Qualifikationen

• PhD or Master’s degree in Robotics, ML, or related field.
• Experience with humanoid or dexterous manipulation.
• Strong Python, PyTorch, and distributed training expertise.
• Expertise in Diffusion Models, Flow Matching, and Transformers.
• Hands-on experience deploying controllers on real robot hardware.
• Experience with RL and simulation environments (IsaacLab, MuJoCo).

Aufgaben

• Scalable Egocentric Pre-training: Architect and implement large‑scale pre‑training objectives for egocentric video datasets to learn generalizable representations of hand‑object interactions and spatial‑temporal dynamics.
• VLA Foundation Modeling: Develop and scale multi‑modal Foundation Models that unify visual perception and natural language instructions into actionable robotic trajectories.
• Generative Policy Design: Design and optimize generative action heads using Diffusion Models and Flow‑matching techniques to capture the multi‑modal distribution of complex human movements.
• Humanoid Motion Alignment: Develop novel algorithms to align human‑centric video representations with the kinematic constraints of 20+ DoF humanoid systems, ensuring fluid and stable execution.
• Reinforcement Learning & Fine‑tuning: Utilize Offline RL and high‑fidelity simulation fine‑tuning to optimize foundation model performance for high‑success‑rate physical manipulation.
• Cross‑Functional Research: Translate cutting‑edge research in scaling laws and world models into production‑ready architectures that enhance robot reliability and autonomy.

Kenntnisse

Python

PyTorch

Distributed training

Diffusion Models

Flow Matching

Transformers

Reinforcement Learning

Robot manipulation

Egocentric vision

Simulation environments

Ausbildung

PhD or Master’s in Robotics/ML

Tools

MuJoCo

IsaacLab

NCCL

Jobbeschreibung

Flexion Robotics seeks an AI Research Engineer to lead dexterous manipulation and egocentric model development. You will build Vision‑Language‑Action models enabling humanoid robots to interact with the world with human‑like fluidity.

You’ll work in our Zürich office on state‑of‑the‑art learning‑based controllers, bridging video observations with high‑DOF robot policies for reliable, flexible manipulation.