About the role 🚀

We are looking for a passionate Senior Data Scientist expert in Document AI (OCR, NER, Table Extraction, and NLP) and/or medical coding inference/consistency (ICD/CPT/DRG…) to join our team in Paris. We would like someone with proven experience in fine-tuning Document AI models for complicated use cases and/or medical coding inference/consistency.

What you will do 👊

As a member of the Data Science team, alongside our technical experts, you will get an opportunity to:

• Learn about health data and healthcare insurance dynamics

• Work on computer vision, Document AI and NLP

• Use LLMs with fine-tuning and RAG applications

• Help in the deployment of the models in production

• Fine-tune models for medical coding related tasks (medical coding inference/consistency)

• Explore client’s dataset to create the best ML pipeline to solve the problems

• Write papers, blog posts and open-source some trained models

• Help maintain and scale our internal AI package

• Improve the fraud detection models

Who you are 😀

• 5+ experience as a Data Scientist/DL/ML Engineer

• Expert in Document AI (OCR, NER, Table Extraction) with proven experience on different projects deploying these models

• Expert in medical coding inference/consistency with proven experience in these topics

• A great theoretical and technical background on Deep Learning

• Very curious about the new advancements on AI, up to date with the SOTA

• Strong communication and presentation skills, with the ability to convey complex concepts to non-technical audiences

• Experience in reading and implementing research papers

• Experience in putting and maintaining models in production

• Very good coding skills in Python, Pytorch and HuggingFace

• Fluent in English (Both Verbal and written). Any additional language is a plus

Bonus skills 🤩

• Previous experience in healthcare or health insurance domain

• Experience with MLFLOW and other MLOps tools

• Experience on pre-training Document AI models

• Screening interview: 45min

• Deep Learning interview (1hr)

• Data Science/ Machine learning/ coding interview (1hr)

• Fit interview with CTO (1hr)