About the role
Responsibilities:
- Build prototypes and production-oriented components for clinical information extraction and LLM workflows.
- Implement prompts, RAG pipelines, fine-tuning experiments, extraction logic, evaluation scripts, and error-analysis tools.
- Work with senior engineers to improve model quality, robustness, and reliability.
- Analyse clinical-text model failures and propose meaningful improvements.
- Collaborate with Clinical AI Data Specialists to understand labelling guidelines, data quality issues, and clinical edge cases.
- Collaborate with ML Evaluation Engineers to run benchmark and regression tests.
- Write clean, tested, maintainable Python code and contribute to internal tools, data processing scripts, and annotation/evaluation workflows.
Requirements:
- 1.5-4 years of hands-on experience in ML, NLP, LLMs, or data-intensive software engineering.
- Strong Python programming skills and willingness to work with messy real-world data.
- Familiarity with PyTorch, HuggingFace, embeddings, transformers, RAG, prompt engineering, and basic fine-tuning.
- Good understanding of precision/recall/F1 train/validation/test splits, overfitting, error analysis, and experiment tracking.
- Ability to learn clinical domain concepts and ask clarifying questions about labels and data.
- Strong ownership of assigned modules and tasks.