Deep Learning Engineer - OCR and Image Captioning
South San Francisco
As a Deep Learning Engineer at Simbe Robotics, you will be part of a talented team designing and training state of the art deep learning algorithms to identify placement, presentation, pricing, and availability of products in retail stores across the globe.
In this role you will lead various initiatives designing, developing, and training in-house character recognition and image caption algorithms powered by deep learning.
- Participate in planning and prioritizing, write functional specifications and lead design reviews for our character recognition and image caption algorithms.
- Generate, clean, and curate real world training datasets
- Create photorealistic synthetic training data for augmentation
- Develop, test, tune, and deploy character recognition and image caption systems across a wide variety of customers
- Evaluate existing character recognition and image caption methods for speed and accuracy performance improvements
- Assist with other deep learning models for image segmentation and object recognition
- Collaborate with other developers, quality engineers, product managers, and documentation writers
- Ph.D. or M.S. preferred
- Strong machine learning background, with 2+ years of hands-on experience in building real systems
- Deep understanding of state of the art machine learning and deep learning algorithms, techniques and best practices
- Solid understanding of linear, non-linear, and dynamic programming
- Experience using or building synthetic image generation systems, data augmentation pipelines, and OCR/image caption systems
- Proficient in at least one of the following: Tensorflow, Keras, PyTorch. Tensorboard knowledge is a plus
- Must be fluent in Python, other languages are a plus
- Should be familiar with training and running deep learning models on GPUs (both commodity and otherwise)
- A good understanding of recurrent neural networks (including LSTMs and GRUs)
- Experience in debugging and diagnosing performance problems with ML algorithms
- Must have excellent written and verbal communication skills
- Experience with attention models, text localization, Google Cloud Platform, AWS, and serverless is a plus
- Strong Linux & Command Line background
- Ability to work hands-on in cross-functional teams with a strong sense of self-direction
We value diversity at our company. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, or any other applicable legally protected characteristics in the location in which the candidate is applying.
For job positions in San Francisco, CA, and other locations where required, we will consider for employment qualified applicants with arrest and conviction records.