ML Engineer

Requirements:
Bachelor's or higher degree in Computer Science, Machine Learning,
or a related field.

Proven experience in maintaining and enhancing machine learning
systems, preferably in document processing.

Strong proficiency in Python and relevant machine learning libraries/
frameworks like TensorFlow, PyTorch

Proven expertise in working with Image Transformer models,
particularly those designed for document image understanding like
Microsoft's DIT

Demonstrated experience in implementing and working with self-
supervised learning techniques, especially in the context of pre-
training models on large-scale unlabeled text images. Familiarity with
approaches like Microsoft's DiT for Document Al tasks.

Hands-on experience in applying Transformer models to various
Document Al tasks, including document image classification,
document layout analysis.

Proven ability to leverage self-supervised pre-trained models, like
DiT, as backbone networks to achieve state-of-the-art results in
downstream tasks.

Proficient in designing experiments, analyzing results, and fine-tuning
models to achieve optimal performance on Document Al tasks. Ability
to interpret and communicate experiment results effectively.
Familiarity with integrating Transformer models into OCR pipelines
and collaborating with OCR technologies for enhanced text detection
and extraction capabilities.

Solid understanding of image processing techniques with a focus on
leveraging OpenCV for tasks such as resizing, feature extraction, and
other pre-processing steps essential for document image analysis
and understanding.

Familiarity with cloud platforms (e.g., AWS, Azure) and
containerization (e.g., Docker).

Excellent problem-solving skills and ability to work independently.
Strong communication skills and ability to collaborate with cross-
functional teams.

Responsibilities:

Maintain and optimize the existing document code prediction system.
Collaborate with cross-functional teams to understand business
requirements and implement enhancements.

Monitor system performance and troubleshoot issues as they arise.
Stay updated on the latest advancements in machine learning and
implement improvements to the prediction model.

Explore and identify new machine learning opportunities within the
document processing domain.