Description

In this role, you will enhance document processing by driving semantic parsing and improving algorithms. Your day-to-day responsibilities will involve hands-on quality improvements, mentoring teammates, and staying at the forefront of research in computer vision.

Requirements

• •Passion for building and improving machine learning systems
• •Proven track record of delivering computer vision systems
• •Comfortable working independently or in a team
• •Creativity and determination in problem-solving
• •5+ years of experience solving recognition problems
• •Fluency in C++ and Python
• •Experience running ML models on mobile devices
• •Experience with machine learning frameworks (Pytorch, Jax, Tensorflow)
• •Skilled in software design, problem-solving, and debugging
• •Experience in computer vision systems or fine-tuning vision-language models is a plus

Tasks

• •Drive semantic document parsing for customer use cases
• •Participate in all phases of quality improvements
• •Define and track performance metrics
• •Prototype and test new features
• •Integrate existing models and create new models
• •Collect and analyze data
• •Debug and optimize algorithms
• •Stay updated on research in document classification and text recognition
• •Identify opportunities to enhance recognition capabilities
• •Mentor team members on code quality and engineering practices

Tools & Technologies

Benefits