Job Information
Affectiva Computer Vision Scientist in Boston, Massachusetts
Job Duties:
Computer Vision Scientist to join the computer vision and machine learning experts on our Cabin Monitoring team, which is building key functionality for our next-generation Automotive Interior Sensing product – novel automotive technology that will significantly improve road safety and will transform our transportation experiences.
S pecific job duties include:
Research, implement, and enhance new and existing algorithms to advance training and testing capabilities for automotive monitoring system;
Collaborate and Communicate: Work closely with other developers and engineers to support the creation of computer vision/machine learning-based features to meet product requirements.
Analyze and improve the efficiency of algorithms: Implement and improve new algorithms, or adaptations to existing algorithms, that will enable novel training and testing capabilities.
Develop features using computer vision and a variety of machine learning methods including detection, classification, temporal machine learning techniques and activity/gesture recognition.
Develop and enhance computer vision/machine learning-based features for Automotive Interior Sensing products;
Investigate tradeoffs between accuracy and computational efficiency for edge/embedded environments and propose solutions to meet run-time requirements;
Develop and maintain KPI reports to measure and analyze product model performance;
Contribute to shared machine learning infrastructure, including data preparation, model training, embedded conversion and benchmarking/KPI generation.
Coordinate with the engineering and QA teams to finalize and test model integration.
Position requirements:
Master's degree in Mechanical engineering, Computer Science, Electrical Engineering, Robotics Engineering or a closely related field, and two years of experience using computer vision, machine learning, and deep learning techniques.
Experience, which may be gained concurrently, must include 3 or more of the following:
2 years of experience working with deep learning frameworks such as
TensorFlow/Keras or PyTorch, including implementing custom layers.
2 years of experience developing applications using C++, MATLAB and Python.
2 years of experience performing Exploratory data analysis using scikit-learn/Scipy/ Jupyter notebook/ Pandas.
2 years of experience optimizing C++ code as well as deep learning models.
2 years of experience deploying neural network models on different hardware.
2 years of experience working with object detection models (YOLO variants, RCNN model variants).
2 years of experience working on object tracking models (Sort, Deep-SORT, optical flow)
1 year of experience in Key point detection (Key-Point RCNN, Open Pose) and Image Segmentation (UNet, UNet++, Mask-RCNN).
1 year of experience with camera calibration and depth estimation.
1 year of experience working with traditional computer vision methods for image classification (Support Vector Machine, Principal Component Analysis, Linear Discriminant Analysis).
1 year of experience establishing data storage pipelines using storage services (e.g. AWS S3) and training using cloud computing platforms (like AWS EC2 or GCP).
1 year of experience implementing Linear Algebra, Probability and Statistics related concepts.
1 year of experience designing efficient end-to-end training pipelines for deep learning model training.
Additional Information and Company Benefits:
Full-Time Position located in downtown Boston
Competitive benefits package including health, dental, vision, life insurance, long-term and short-term disability
401K matching
Unlimited PTO
Casual startup office culture, collaborative office space
Flexible work schedule
Complimentary snacks, drinks, and weekly team lunch.
We are an equal opportunity employer and value diversity at our company. We do not discriminate on the basis of race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status.
Powered by JazzHR