Candidate Profile — Candidate #2
Position: FieldAI — Robotics AI Engineer (Irvine, CA)
Candidate Location: Sacramento, California
Experience: 7.8 years experience
Relevant Experience & Education Highlights
Brings hands-on ROS2 expertise in developing perception, SLAM, and path planning for legged robots, directly aligning with designing Field Foundation Models, Dynamics Foundation Models, and ROS-integrated autonomous systems at FieldAI.
1. Algorithm Development
Designed and implemented perception, SLAM, and path planning algorithms for autonomous robotic prototypes in unstructured environments.
- Developed ROS2 software stack for quadrupedal robotic prototype, focusing on SLAM, perception, and path planning for real-world deployment.
- Designed multi-node system employing visual odometry to construct point clouds from RGBD images, enhancing environmental mapping.
- Integrated multimodal RGBD-LiDAR systems using Octomap, PCL, Open3D, Voxel Grid Filters, and ORB-SLAM3 for robust perception on custom platforms.
- Implemented deep learning controls for ankle exoskeletons using TCN models to predict gait phases and generate biologically inspired torque.
2. Software Integration and Testing
Integrated and tested robotic software modules with ROS2, ensuring reliable performance in simulation and real-world scenarios.
- Developed ROS2 modules for quadrupedal robot, including testing SLAM and path planning in dynamic environments.
- Built software solutions with Django-Python backend, ReactJS frontend, MySQL, WebSockets, and HTTP for real-time LLM-based RAG chatbots.
- Applied anomaly detection using Autoencoders, VAEs, GANs, and ensembles for exoskeleton control in in-distribution and out-of-distribution scenarios.
3. Hands-On Robotics Deployment
Gained practical experience deploying and testing robotic systems across diverse platforms like legged robots, exoskeletons, drones, and climbers.
- Contributed to quadrupedal robot prototype development at a robotics startup, focusing on field-deployable perception and navigation.
- Designed manipulators for aerial drones with RGB-D camera and GPS sensor integration for obstacle avoidance and object manipulation.
- Developed modular pipe climber mechanisms at a research institute, testing in challenging environments.
- Implemented TCN-based controls for ankle exoskeletons, fully automating gait prediction and torque mapping.
Requirements & Candidate Alignment
| FieldAI Requirement | Candidate Qualification |
|---|---|
| Strong programming skills: Proficiency in Python and C++ for algorithm development and system integration. | Proficient in Python via Django backends, ML models, and data analysis; multithreading expertise supporting C++ integration in robotics. |
| Proficiency in ROS (Robot Operating System): Experience developing and integrating robotic software solutions. | ROS2 expertise developing full software stacks for quadrupedal prototypes, including SLAM and perception modules. |
| Hands-On Robotics Experience: Practical experience working with autonomous robotic systems, including testing and deployment in the field. | 7.8 years hands-on with quadrupedal robots, ankle exoskeletons, aerial drones, and pipe climbers, including sensor integration and field testing. |
| Understanding of Planning and Controls: Solid knowledge of path planning, control theory, and trajectory optimization. | Path planning implementation for ROS2 quadrupedal robots; control theory applied in TCN-based exoskeleton torque prediction. |
| **Advanced degree (Bachelors, Master's) in Robotics, Computer Science, Electrical Engineering, or a related field. | MS in Robotics from a top-tier research university; BS in Mechanical Engineering from a reputable engineering college. |
| Experience with humanoid or legged robots. | Quadrupedal robot development using ROS2 for SLAM, perception, and path planning at a robotics startup. |
| Familiarity with sensor integration and perception algorithms. | Integrated RGBD-LiDAR sensors with visual odometry, point clouds, OpenCV, and ORB-SLAM3 for robotic perception. |
| Knowledge of machine learning techniques applied to robotics. | Applied deep learning including TCN, Autoencoders, VAEs, GANs for exoskeleton control and anomaly detection. |
If you would like to discuss this candidate or other critical roles, here is a link to my calendar to schedule a call:
Schedule a CallContact:
Finding the signal in the noise since 2005