Tasks & Responsibilities:
1. Review and optimize a transformer architecture and training pipeline.
2. Implement and experiment with advanced techniques to improve performance on fields with severe class imbalance.
3. Conduct in-depth error analysis to identify patterns in misclassifications and propose data-driven improvements.
4. Refine and validate the data processing, label mapping, and stratified data splitting procedures to ensure maximum reliability.
5. Collaborate with our software architect to integrate the final, optimized model into a production-ready API for inference
6. Document the final model architecture, training procedures, performance benchmarks, and best practices for future development.
Must Haves:
7. Educational background: advanced degree in AI/NLP or related field
8. Min. 3 years hands-on experience fine-tuning Transformer models
9. Demonstrable experience with multi-task and multi-label classification problems, expertise in handling severe class imbalance in text data
10. Proficiency in deploying machine learning models as REST APIs
11. Strong proficiency in PyTorch, including creating custom model architectures (e.g., multi-head classifiers) and custom loss functions
12. Strong software engineering fundamentals and the ability to write clean, modular, and well-documented Python code, experience with Docker
13. Professional proficiency in English
14. Strong analytical and problem-solving skills, and collaboration abilities.
Nice to Haves:
15. Direct experience working with biomedical, scientific, or other technical document formats.
16. Familiarity with advanced data splitting techniques for multi-label datasets.
17. Experience with MLOps principles and tools.