About the role
Responsibilities:
- Design and implement GenAI solutions for medical report understanding and code mapping using LLMs and prompt engineering.
- Build and optimise RAG (Retrieval Augmented Generation) systems for accurate and reliable medical coding.
- Develop and deploy AI agents for multi-speciality medical coding automation.
- Evaluate, benchmark, and select appropriate foundation models (GPT, Claude, Llama, etc. ) for healthcare use cases.
- Implement cost-effective, production-ready GenAI architectures with monitoring and observability.
- Transform existing rule-based systems into GenAI-powered solutions while maintaining accuracy and compliance.
- Collaborate with clinical teams to ensure outputs align with healthcare standards and regulations (HIPAA, ICD-10 CPT, and SNOMED-CT).
- Conduct A/B testing, model evaluation, and continuous performance optimisation.
- Stay updated with the latest GenAI/LLM research and bring relevant techniques into production.
Requirements:
- 3+ years of hands-on experience with LLMs/GenAI (GPT, Claude, Llama, PaLM, etc. ).
- 3+ years overall in data science/ML engineering.
- Strong proficiency in Python with GenAI libraries (LangChain, LlamaIndex, HuggingFace, OpenAI/Anthropic APIs).
- Exposure to healthcare NLP (clinical reports, medical coding, and terminologies).
- Deep understanding of RAG architectures, embeddings, and vector databases (Pinecone, Weaviate, Chroma).
- Production deployment experience: scaling, monitoring, cost optimisation, and MLOps practices.