About the job
Apptronik is a human-centered robotics company developing AI-powered robots to support humanity in every facet of life. Our flagship humanoid robot, Apollo, is built to collaborate thoughtfully with people, starting with critical industries such as manufacturing and logistics, with future applications in healthcare, the home, and beyond.
We operate at the cutting edge of Applied AI, applying our expertise across the full robotics stack to solve some of society's most important problems. You will join a team dedicated to bringing Apollo to market at scale, tackling the complex challenges like safety, commercialization, and mass production to change the world for the better.
JOB SUMMARY
The Senior Perception Learning Engineer is a key, hands-on role. You will build the learned perception that lets Apollo see and understand people, objects, and its work area at customer sites. You will design, train, and deploy deep learning models for detection, tracking, segmentation, depth, and 3D scene understanding. These models give navigation, manipulation, safety, and human-robot interaction the data that they need. The main focus of this role is to move models from research to fast, reliable use on the robot's onboard compute. As a senior member of the team, you will also mentor engineers and raise the team's engineering standards.
ESSENTIAL DUTIES AND RESPONSIBILITIES or KEY ACCOUNTABILITIES
- Design, train, and optimize deep learning models for object detection, tracking, segmentation, pose estimation, and 3D scene understanding on humanoid robots.
- Build perception for safety near people. Detect and track people reliably in all site conditions, and work with the safety team on test evidence for these models.
- Develop multi-sensor fusion for cameras, depth sensors, and other sensors. Give the robot a real-time model of the space around it, for example obstacles and free space.
- Build scalable data pipelines, training infrastructure, and evaluation tools. Use data from the field to retrain and improve the models.
- Deploy models on edge hardware within strict latency, accuracy, compute, and thermal limits. Use profiling, quantization, and regression tests to keep them there.
- Use synthetic data from simulation frameworks such as Isaac Sim together with real-world data to improve model generalization and robustness.
- Work closely with the autonomy, navigation, controls, reinforcement learning, and platform teams. Define clear perception interfaces that meet real-time needs.
- Mentor engineers through technical guidance, design reviews, and code reviews. Improve code quality, model versioning, reproducibility, and release practices.
SKILLS AND REQUIREMENTS
- Strong background in deep learning for computer vision: detection, segmentation, multi-object tracking, and 3D perception.
- Hands-on experience with modern AI frameworks (PyTorch, JAX, TensorFlow) and computer vision libraries such as OpenCV, Detectron2, and YOLO.
- Strong Python and modern C++, with good software engineering practice: version control, testing, and CI/CD.
- Good knowledge of 3D geometry, camera models, and depth estimation.
- Experience deploying optimized models on edge hardware (GPU, NPU, or embedded platforms) under compute, latency, and thermal limits.
- Strong plus: experience with foundation models for perception and language, for example SAM, CLIP, DINOv2, or Flamingo.
- Strong plus: experience with model acceleration, quantization, or compression (TensorRT, ONNX Runtime), and with real-time middleware such as ROS 2, GStreamer, or zero-copy pipelines.
- Strong plus: knowledge of synthetic data generation and domain adaptation.
- A results-oriented mindset. You want to see models work reliably on real hardware.
EDUCATION and/or EXPERIENCE
- An MS or PhD in Computer Science, Robotics, Computer Engineering, or a related field and 3+ years of industry experience, or a BS and 5+ years.
- A proven record of shipping ML perception systems from R&D into production robotics or real-time vision products.
- Experience with humanoid robots, legged robots, or manipulation is a plus.
- Experience as a mentor or technical guide to other engineers on a team.
- Plus: publications at relevant conferences (for example CVPR, ICCV, ECCV, CoRL, RSS, or ICRA) or contributions to open-source robotics or vision software.
PHYSICAL REQUIREMENTS
- Prolonged periods of sitting at a desk and working on a computer
- Must be able to lift 15 pounds at times
- Vision to read printed materials and a computer screen
- Hearing and speech to communicate
The annual salary range is $220,000 - $250,000
*This is a direct hire. Please, no outside Agency solicitations.
Apptronik provides equal employment opportunities to all employees and applicants for employment and prohibits discrimination and harassment of any type without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state or local laws.
Job text from Apptronik's careers site.