Leads the team this role joins
In-house, owns the opening
Director or head of the group
From your own Gmail and LinkedIn.
About the role
This is a full-time, onsite senior role in Sunnyvale, California, for an engineer who builds perception and SLAM systems for humanoid robots. The work centers on learning-based perception, multi-sensor fusion, and training and deploying models that run on real robots. Apptronik makes humanoid robots for manufacturing and logistics. The role asks for at least three years of experience shipping perception or SLAM systems.
What you’ll do
- Lead the design, development, and tuning of perception and SLAM pipelines for humanoid robots.
- Build multi-sensor fusion that combines cameras, LiDAR, depth sensors, and IMUs for real-time state estimation.
- Contribute to data pipelines, training infrastructure, and inference frameworks.
- Research and deploy learning-based models for SLAM, 3D scene understanding, and perception.
- Profile, test, and monitor perception modules against latency, accuracy, and reliability targets on edge devices.
- Work with planning, control, and hardware teams on perception-to-action interfaces.
- Combine synthetic simulation data with real-world datasets to improve generalization.
- Maintain code quality, model versioning, and reproducibility.
What they’re looking for
- An MS or PhD in computer science, robotics, computer engineering, or a related field.
- At least three years building and shipping perception or SLAM systems.
- Strong grounding in SLAM, visual-inertial odometry, and probabilistic state estimation.
- Practical experience with detection, segmentation, tracking, and 3D perception.
- Experience with PyTorch, JAX, or TensorFlow, and OpenCV.
- Proficiency in Python and modern C++ with solid software engineering practice.
- Understanding of 3D geometry, camera models, and estimation methods such as EKF, UKF, and factor graphs.
- Experience deploying optimized models on GPU, NPU, or embedded hardware.
- A track record of moving ML or SLAM work into production robotics platforms.
Nice to have
- Experience with humanoid robots, bipedal locomotion, or manipulation.
- Experience with SLAM frameworks such as ORB-SLAM, VINS, Kimera, or Cartographer.
- Classical computer vision skills such as geometry-based methods and feature extraction.
- Model acceleration or compression with TensorRT or ONNX Runtime.
- Experience with ROS 2, GStreamer, or zero-copy pipelines.
- Synthetic data generation and domain adaptation.
- Contributions to open-source robotics or vision software.
What’s on offer
- Base salary listed between $220,000 and $250,000 per year.
Skills
Questions about this role
Is this role remote?
No. The posting lists the role as onsite in Sunnyvale, California.
What salary does the role pay?
The posting lists $220,000 to $250,000 per year.
How many years of experience do I need?
At least three years building and shipping perception or SLAM systems.
Do I need a graduate degree?
Yes. An MS or PhD in a related field is required.