Lead Machine Learning Engineer

Position Summary: We are seeking a Senior Machine Learning Engineer to lead the development of advanced Vision-Language Models (VLMs) tailored for healthcare applications. This role involves leveraging transfer learning techniques to create models capable of interpreting and processing complex medical documents, including forms, charts, and handwritten notes.
Key Responsibilities

Model Development: Design and implement VLMs using transfer learning to process and understand medical documents, focusing on visual layouts and textual content.

Data Management: Oversee the collection, annotation, and preprocessing of large-scale medical datasets to train and validate machine learning models.

Algorithm Optimization: Enhance model performance through hyperparameter tuning, feature engineering, and the application of state-of-the-art machine learning algorithms.

Collaboration: Work closely with cross-functional teams to integrate AI solutions into existing workflows.

Research and Innovation: Stay abreast of the latest developments in machine learning and AI, particularly in the healthcare sector, to drive continuous improvement and innovation.
Required Qualifications

Educational Background: Master's or Ph.D. in Computer Science, Machine Learning, Artificial Intelligence, or a related field.

Experience: Minimum of 5 years in machine learning engineering, with a focus on natural language processing and computer vision. Experience in the healthcare industry is highly desirable.
Required Technical Qualifications

Machine Learning Expertise:
— In-depth knowledge of Vision-Language Models (VLMs) and their application in document understanding.
— Proficiency in Retrieval-Augmented Generation (RAG) techniques to enhance document comprehension and reasoning capabilities.
— Familiarity with transformer architectures (e.g., BERT, GPT, Vision Transformers) and experience adapting them for multimodal data processing.
— Solid experience with transfer learning methodologies to leverage pre-trained models effectively.
— Proficiency in multi-task learning to train models that handle different types of tasks (e.g., classification, object detection, entity extraction).

Advanced Computer Vision Skills:
— Expertise in Optical Character Recognition (OCR) technologies and integrating OCR with NLP for comprehensive document analysis.
— Experience working with layout-aware models such as LayoutLM or other document-focused architectures that account for page structure and visual cues.

NLP and Language Modeling:
— Strong background in Natural Language Processing (NLP), including named entity recognition (NER), text classification, and relation extraction.
— Hands-on experience with sequence-to-sequence models and encoder-decoder frameworks for complex data extraction.

Data Engineering and Processing:
— Skilled in handling large-scale annotated medical datasets and applying techniques for efficient data labeling and augmentation.
— Ability to develop and implement data pipelines that manage structured and unstructured data, including medical forms, tables, and handwritten notes.

Model Evaluation and Optimization:
— Proficiency in model benchmarking, with experience in developing models that maintain high accuracy (e.g., >96%) after extensive training on customer-specific data.
— Expertise in confidence interval estimation for models, with a focus on ensuring model output reliability and enabling automated workflows.
Preferred Technical Skills

Knowledge of Generative AI:
— Familiarity with Generative Adversarial Networks (GANs) and their application in data augmentation or synthetic data generation.
— Experience with context-aware generation and adaptive learning techniques for document-specific rule sets. > Sahand Soltanieh: Distributed Systems and Scalability:
— Ability to deploy and manage machine learning models in cloud environments (e.g., AWS, GCP, Azure) for scalable solutions.
— Understanding of distributed training frameworks such as Horovod or PyTorch Distributed Data Parallel (DDP) for large model training.

Tool Proficiency:
— Experience with MLOps tools like MLflow, Kubeflow, or TFX for streamlined model development and deployment.
— Familiarity with containerization technologies such as Docker and orchestration tools like Kubernetes for production deployment.

Industry Knowledge:
— Understanding of medical terminologies.
— Experience developing AI solutions compliant with data privacy standards.
Benefits:
— Competitive salary and performance-based bonuses.
— Opportunities for professional development and continuous learning.
— Flexible work environment with options for remote work.
Application Process: Interested candidates are invited to submit their resume, a cover letter detailing their relevant experience, and examples of previous work or projects. Please also send a copy of your application to "*******" with the subject line "Lead Machine Learning Engineer Application."