Modeling & Simulation Engineer, Robotics
Andromeda Robotics
·Yesterday
- Salary
- $150k – $220k/yr
- Location
- San Francisco, California
- Workplace
- Onsite
- Type
- Full-time
- Department
- Engineering
- Experience
- 2+ years
- Source
- Workable
Description
The Bigger Picture
At Andromeda, we're building the social intelligence layer for humanoid robots - technology that
allows robots to understand people, build relationships and become a meaningful part of everyday life.
Our first robot, Abi, is already doing this in aged care and healthcare, where she brings conversation, companionship and engagement to people every day.
Now we're scaling from early deployments into a platform that can operate across thousands of real-world environments. We're looking for individuals who want to tackle hard problems across robotics and AI, and help define what it means for robots to live and interact alongside people.
The Role
When can we trust a simulated robot?
Andromeda is building the Social OS for robots, starting with Abi: a robot that interacts with people in care environments. As we expand what Abi can do, we need to test more behaviors and failure conditions than physical trials alone can cover.
That makes simulation essential. It also makes its accuracy consequential.
We are hiring a Modeling & Simulation Engineer to own the models of Abi's sensors, actuators, and physical dynamics, and establish how well they predict the real robot. You will decide which differences matter, close them through measurement and modeling, and define where simulation is sufficient and where hardware evidence is necessary.
You will own the infrastructure that runs simulations and tests. You own the physical models and their validation. Together, you will give perception, actuation, and autonomy engineers a reliable basis for development and verification.
The Opportunity
The first challenge is current-generation Abi. The longer-term challenge is maintaining confidence as the hardware, autonomy, and robot embodiments change.
You will establish the modeling discipline behind that work: what we model, how we measure its accuracy, and which engineering decisions the evidence supports. This is an opportunity to shape how successive robots are designed and tested, withdirect access to the hardware and the teams building it.
What you will own
- Models of robot dynamics, sensors, and actuators that capture the behavior relevant to development and testing, including non-ideal operation.
- The measurement and system-identification work needed to reduce sim-to-real error, with quantitative evidence of improvement.
- Model verification and validation: correct implementation, agreement with physical measurements, and explicit limits of use.
- Fault modeling that exposes weaknesses in the robot's response to degraded sensing, actuation, and communications.
- Integration of these models into the shared simulation and testing framework, alongside the Simulation Platform Engineer and domain teams.
- You will set the technical approach and fidelity priorities. The measure of success is whether the models help engineers find failures and make better decisions about the real robot.