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