Vijay Rajanna
Principal Research Engineer @Harmoneyes
Signup · Get unlimited contacts
WORK HISTORY
Principal Research Engineer @Harmoneyes
San Jose, CA, US
In this role, I am leading research and development efforts in the areas of eye tracking and artificial intelligence to create real-time, high-fidelity, human perception systems. This involves architecting novel machine learning models that predict, in real-time, an individual’s fatigue level, cognitive load, cybersickness, reading comprehension, and other performance-related attributes based on the eye movement data.I also collaborate closely with neuroscientists to research and develop algorithms that extract distinctive eye movement features to maximize predictive accuracy of a person’s state, encompassing attention, health, and performance.
EDUCATION
Birla Institute of Technology and Science, Pilani
Master's Degree, Computer Science - Software Systems
Texas A&M University
Doctor of Philosophy (Ph.D.), Computer Science - Human-Computer Interaction - Eye Tracking
Visvesvaraya Technological University
Bachelor's Degree, Computer Science and Engineering
SKILLS
ABOUT VIJAY RAJANNA
Profile: I am a Machine Learning and Computer Vision researcher specializing in ML modeling and algorithm development. Currently at HarmonEyes, I lead research and development of eye-tracking–based ML systems that deliver real-time, high-fidelity predictions of cognitive load, fatigue, and attention. Previously, I spent over six years at Sensel, where I played a key role in developing the world\'s most advanced touch, force, and haptics technologies. Today, leading OEMs such as Lenovo, Dell, and Microsoft ship laptops featuring Sensel’s haptic touchpad/technology integrated into their devices. At Sensel, I developed computer vision and ML models for precise touch tracking, accurate force sensing, and immersive haptic experiences, advancing the interface between humans and digital systems. My work spans perception systems, human–computer interaction, novel input technologies, eye tracking, industrial robotics vision, and AR/VR, with research translated into commercial products used by millions of users. Doctoral Dissertation- My doctoral dissertation research focused on advancing accessibility in Human-Computer Interaction by developing innovative gaze-assisted, multi-modal interaction methods to enable individuals with impairments to effectively engage with computing devices. Additionally, I developed machine learning models to perform predictive analytics on eye movement data, with practical applications in cybersecurity, educational technology, and behavioral economics. Technology, Tools, and Frameworks- Programming Languages / Frameworks: C, C++, Qt C++, C#, WPF, Python, MATLAB, OpenCV, SPSS, HTML, SQL Machine Learning: Classic Machine Learning Methods, Supervised and Unsupervised Methods. Regression and Classification, Feature Engineering, Dimensionality Reduction, Regularization, Cross-Validation Methods, Supervised and Unsupervised Clustering, Hyperparameter Optimization, Neural Networks, Deep Learning, Batch and Layer Normalization Techniques, Time Sequence Modeling, RNN, LSTM, Convolutional Neural Networks (CNNs), Transformers, LLMs, Attention Mechanisms, LLM fine-tuning, PyTorch, Scikit-learn, NumPy, Pandas, SciPy, Matplotlib. Computer Vision: Signal Processing, CNN-based Computer Vison Models for object detection, Vision-Language Models (VLM), OpenCV algorithms for Image Segmentation, Object Detection, Tracking, Optical Character Recognition, Shape Detection.
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.