Junior Annotator (Machine Learning / Computer Vision) (IRC280386)

Job Description

- High attention to detail and commitment to annotation accuracy.

- Comfort working with 2D/3D medical imaging data.

- Experience with or willingness to learn tools like 3D Slicer, Amazon SageMaker Ground Truth, CVAT or similar.

- General understanding of Machine Learning & Computer Vision models idea would be a big plus.

- Background in medicine, radiology, biomedical sciences, anatomy, or related healthcare fields is a big plus.

- Basic understanding of QA Process and Methodologies would be a plus;

- Experience working in healthcare AI, research, or imaging is a plus.

- Strong communication skills and at least upper-intermediate English level for effective cooperation with client.

Job Responsibilities

We are looking for a detail-oriented Annotator to prepare the foundational data for our ML models. Your meticulous work will be crucial in ensuring the accuracy and quality of the datasets that will power this transformative change.

Initially, you will focus on preparing data related to our highest-volume staples (one linear and one circular design). Your responsibilities will directly contribute to building a production-ready analytical solution that will revolutionize testing and quality assurance for surgical devices.

Your responsibilities will include

- Prepare datasets for training machine learning models that automatically detect information on medical device images.

- Close work with a client team with planning work load, results demonstration and requirements clarification;

- Analyze defects and problems in current algorithms based on video output;

- Raise a flag when any defect occurs, verify if test sets are have acceptable output;

- Quality Assurance: Follow strict medical annotation protocols provided by supervising doctors.

- Collaboration: Work closely with medical experts, AI engineers, and fellow annotators in a multidisciplinary environment.

Key Contribution: You will be the essential link between raw engineering data and the machine learning models that will automate and accelerate our product validation process.

Department/Project Description

We are launching a critical initiative to integrate advanced Artificial Intelligence (AI) and Machine Learning (ML) into the product development and validation process for high-volume surgical staples.

This project aims to solve current process inefficiencies—specifically, long analysis wait times (up to 4 weeks per test) and high vendor costs—by bringing analytical capabilities in-house and automating the validation of millions of staples annually. This will lead to faster product development and significant cost savings.