Senior Robotics Software Engineer, Simulation

Bonsai Robotics develops affordable, vision-based autonomy that makes off-road equipment smarter, safer, and more productive. We are redefining outdoor autonomy with Bonsai Intelligence, a connected platform that’s inspired by biology to see, think, and act with precision like a human. We bring together advanced perception, embodied AI, integrations with equipment manufacturers, and our compact, modular Amiga vehicles to deliver reliable automation to the world’s most demanding field operations—reducing costs and increasing operational efficiencies.

We are seeking a Senior Robotics Software Engineer, Simulation to build and own our simulation platform. Our machines work in orchards, vineyards, and bedded crops, in changing light and weather, and across several vehicle form factors. Field time is expensive, slow, and seasonal. Simulation is how we close that gap: it is where every software release is regression-tested, where field failures are reproduced and fixed, and where we generate synthetic data to train our perception models. This role owns that platform end to end, from vehicle, sensor, and environment models to the CI pipelines and metrics that tell us whether a change is safe to ship. Above all, we care that what passes in simulation also works in the field. The ideal candidate is a pragmatic robotics engineer who is comfortable from physics and rendering up to CI infrastructure, and who treats "we can only find out in the field" as a bug.

• →Build and maintain simulation environments that model real field conditions, including orchards, vineyards, bedded crops, uneven terrain, and variable lighting and weather.
• →Own the interface between the simulator and our ROS 2 autonomy stack, and build SIL and HIL frameworks that run the full stack (perception, planning, and controls) in closed loop.
• →Turn field logs into simulation: replay recorded drives, reproduce field failures as regression scenarios, and grow a scenario library that covers the edge cases our machines actually encounter.
• →Create and maintain sensor models (cameras, GNSS/RTK, IMUs, LiDAR), including noise and failure modes, calibrated against real hardware.
• →Model vehicle dynamics and terrain interaction for multiple robot form factors, using system identification against real vehicle data.
• →Build automated scenario generation, evaluation metrics, and reporting, so every change to the autonomy stack is tested in simulation in CI before it reaches a machine.
• →Keep simulation fast, deterministic, and reproducible, and measure how well simulation results predict real-world behavior.
• →Generate synthetic data for perception training, working with the ML team on domain randomization and generative methods.
• →Work with the perception, controls, and platform teams to define simulation requirements and prioritize the sim-to-real gaps that matter most.

• Strong computer science fundamentals and systems fluency
• Bachelor's, Master's, or PhD in Computer Science, Robotics, or a related field, with 5+ years of industry experience in robotics software engineering and a significant focus on simulation
• 2+ years building SIL, HIL, or closed-loop evaluation systems used in production
• Strong proficiency in C/C++ and Python, and the ability to read and debug a large existing codebase
• Experience building simulation environments with platforms such as NVIDIA Isaac Sim, MuJoCo, Gazebo, or similar
• Familiarity with physics engines (PhysX, Bullet, MuJoCo, oration
• Deep understanding of ROS 2
• Experience integrating simulation into CI/CD pipelines for
• A pragmatic approach to engineering: you choose the simplest model that answers the question and avoid over-engineering
• Strong debugging, testing, and problem-solving skills, withendently and collaboratively

• Rust programming experience
• Exposure to agricultural, construction, or off-road robotics
• Experience with digital twins or synthetic data generation
• Experience using world models (e.g., NVIDIA Cosmos or similar generative video models) for synthetic data generation or scenario augmentation
• Experience with neural reconstruction (3D Gaussian Splattinon scenes from real sensor data
• Familiarity with USD/OpenUSD scene formats
• Experience with sim-to-real transfer techniques (domain ranication)
• GPU-accelerated rendering or ray tracing for camera simulation
• Experience with NVIDIA Jetson or other embedded deployment

At Bonsai, we're building the future of robotics and we know that means investing in our people. We're committed to creating a workplace where you can do your best work, grow your skills, and feel genuinely part of something bigger.

We operate on a hybrid model because we believe the best collaboration happens both in person and from where you work best. You'll have the flexibility to split your time between our office and home, so you can stay connected to the team while maintaining the balance that works for you.

The best employees are those who create balance in their lives, which is why we prioritize balance and well-being for everyone at Bonsai. We foster a supportive environment where teammates look out for each other.

On in-office days, we've got lunch covered. It's a small thing that makes a big difference, with more time to connect with teammates and less to worry about.

At Bonsai, you're not just part of a team, you're part of a community. We celebrate wins together, support each other through challenges, and genuinely enjoy the people we work with. From team events to cross-functional collaboration, we're building something together.

Every day, you're contributing to advancements in robotics that matter. If you're excited about innovation and impact, you'll find it here.

Bonsai Robotics is an Equal Employment Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, creed, religion, sex, sexual orientation, national origin or nationality, ancestry, age, disability, gender identity or expression, marital status or any other category protected by law.