Job Summary
A company is looking for a Senior Applied Research Scientist, Multimodal Retrieval.
Key Responsibilities
- Develop efficient models and pipelines to extract text content from various modalities including images, video, and audio
- Build vision pipelines for document ingestion, focusing on layout analysis, object detection, and OCR
- Craft datasets and methodologies for research, and assist in scaling pipelines to production capability
Required Qualifications
- Master's, Ph.D., or equivalent experience in retrieval or multimodal research, with a publication track record in leading conferences
- Hands-on experience in developing computer vision models, particularly for document-focused tasks
- Understanding of state-of-the-art retrieval research, especially in multimodal content retrieval
- 10+ years of experience in developing multimodal systems and knowledge of ingestion pipeline best practices
- Excellent Python programming skills and familiarity with deep learning frameworks like PyTorch and TensorFlow
Comments