Robotics Engineer - Modeling&Sim-to-Real Transfer, Zürich (Kreis 11)

About Flexion At Flexion, we're building the intelligence layer powering the next generation of humanoid robots. Our mission is to accelerate the transition from fragile prototypes to real-world humanoid deployment. We are founded by leading scientists in robot reinforcement learning (ex-Nvidia, ex-ETH Zürich), and backed by leading international VC firms. In just months, we’ve gone from our first line of code to deploying real humanoid capabilities.

The Role We’re looking for a Robotics Engineer to help close the gap between simulation and reality. As we deploy learned control policies onto physical hardware, the fidelity of our simulation is a critical factor in our success.

You will focus on the accurate modeling and system identification of in-house and customer robots. You will work directly with the physical hardware to characterize sensors, drivetrains, and contact dynamics, accurately replicate these behaviors in our simulation environment, and evaluate the sim-to-real gap.

In this interdisciplinary role, you will work closely with our control, perception, and hardware teams to maximize the performance of our solutions.

Key Responsibilities

High-Fidelity Modeling: Develop mathematical models for physical subsystems, including drivetrains, sensors, and network behavior (latency, jitter)

System Identification: Design and execute experiments to collect robot data and use it to identify physical parameters (friction coefficients, inertial parameters, noise, latency)

Simulation Implementation: Implement these models into our modern simulation infrastructure

Validation&Verification: Continuously benchmark simulation performance against real-world logs to quantify and minimize the "Sim-to-Real" gap

Qualifications

MSc or PhD in Robotics, Mechanical Engineering, Electrical Engineering, or equivalent experience

Strong background in multi-body dynamics, numerical methods, and robot physics

Proven experience in system modeling and system identification applied to physical systems

Strong coding skills in C++ and Python

Hands-on experience with modern simulators (e.g., Isaac Lab/Gym, MuJoCo, Drake)

Hands-on experience with real robotic hardware running and evaluating experiments and system-level debugging

Additional Skills

Deep knowledge of actuator dynamics (BLDC motors, gearboxes, friction models)

Deep knowledge of sensor modeling (IMUs, LiDARs, cameras)

Familiarity with Reinforcement Learning

Experience with robot description formats (URDF, SDF, USD)

Benefits

Competitive compensation

A front-row seat at one of Europe’s most ambitious robotics companies

An energetic, collaborative team with a bias for action

#J-18808-Ljbffr