Relevant Experience & Education Highlights
Brings deep expertise in ROS2-integrated robotics navigation, GPU-accelerated algorithms with CUDA and PyTorch, sensor fusion, and real-world autonomous systems deployment, strongly aligning with designing risk-aware Field Foundation Models and Dynamics Foundation Models.
1. Algorithm Development
Designed advanced AI-powered models and planning algorithms for navigation, perception, and optimization in dynamic environments.
- Developed visual SLAM auxiliary navigation system incorporating sensor fusion with IMU and LiDAR SLAM, fast initialization, map fusion, and memory management for automated material delivery robots at a large manufacturing company's emerging technology center.
- Implemented robust lane keeping algorithm using RGB images from ultra-low viewpoints, leveraging C++ and CUDA programming within ROS2 at a large manufacturing company's emerging technology center.
- Created neural network models for accelerated MRI reconstruction using incomplete raw data with PyTorch for training on Ubuntu and C++ libtorch for Windows deployment, alongside customizing denoising diffusion probabilistic models at a consumer technology research lab.
- Accelerated feature extraction and descriptor calculation algorithms using C++ ARM Neon, improving vSLAM frame rate from 3fps to 6fps on ARM Cortex M4 processors at a large manufacturing company's emerging technology center.
2. Software Integration and Testing
Integrated and tested autonomous intelligence modules using ROS2, real-time systems, and learning loops for reliable performance.
- Utilized ROS2 with C++ multithreading for real-time embedded systems in visual SLAM navigation and lane keeping for factory robots at a large manufacturing company's emerging technology center.
- Developed offline map management system performing interactive large-scale graph-based optimization to enhance map accuracy, robustness, and coverage using C++ on Ubuntu at a large manufacturing company's emerging technology center.
- Applied sensor fusion technology with millimeter-wave radar, audio, and light sensors for human perception and monitoring at a health technology company.
- Led development of imaging algorithms for fluorescence microscopy systems using C#, Matlab, CUDA programming, and C++/CLI at a medical imaging company.
3. Hands-On Robotics Deployment
Deployed and fine-tuned robotic systems in industrial factory environments, ensuring seamless software-hardware integration.
- Engineered autonomous material delivery robots with visual SLAM, lane keeping, and map management for real-world factory deployment at a large manufacturing company's emerging technology center.
- Directed imaging team in designing automated fluorescence microscopy imaging and analysis systems for cancer diagnostics, including specifications and documentation at a medical imaging company.
- Developed nucleus segmentation methods using tensor voting and local adaptive thresholding, reimplemented from Matlab to C++ for robust detection on IHC slide images at a large manufacturing company's emerging technology center.
Requirements & Candidate Alignment
| FieldAI Requirement | Candidate Qualification |
|---|---|
| Strong programming skills: Proficiency in Python and C++ for algorithm development and system integration. | Proficient in Python, C++, PyTorch, and C++ libtorch, applied in neural networks, ROS2 robotics, and real-time systems. |
| Proficiency in ROS (Robot Operating System): Experience developing and integrating robotic software solutions. | Proficient in ROS2, utilized for visual SLAM, lane keeping, multithreading, and navigation in autonomous factory robots. |
| Hands-On Robotics Experience: Practical experience working with autonomous robotic systems, including testing and deployment in the field. | Extensive hands-on experience deploying autonomous material delivery robots with SLAM and sensor fusion in factory environments. |
| Understanding of Planning and Controls: Solid knowledge of path planning, control theory, and trajectory optimization. | Strong foundation from MS in Control Theory and Applications, demonstrated in SLAM navigation, map optimization, and lane keeping algorithms. |
| Experience with GPU programming (CUDA C++, PyTorch): a significant plus. | Experienced with CUDA C++ for lane keeping and imaging acceleration, and PyTorch for model training and MRI reconstruction. |
| Familiarity with sensor integration and perception algorithms. | Expert in sensor fusion including IMU, LiDAR, millimeter-wave radar, audio, and light sensors for perception and navigation. |
| Knowledge of machine learning techniques applied to robotics. | Applied deep learning, neural networks, and diffusion models to robotics navigation, SLAM, and low-power AI algorithms. |
| Advanced degree (Bachelors, Master's) in Robotics, Computer Science, Electrical Engineering, or a related field. | PhD in Electrical and Electronics Engineering from a top research university; MS in Control Theory and Applications from a leading research institute; BS in Automatic Control from a prestigious engineering university. |
| Exposure to industrial robotics applications in sectors like construction, mining, or manufacturing. | Extensive experience with autonomous robots for material delivery in manufacturing factory environments. |
| Total experience: 20.3 years | 20.3 years across robotics engineering, computer vision, real-time sensing, and AI development roles. |
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