AI Engineer – Retrieval Augmented Generation & LLMs

About the role

We are looking for an AI Engineer to design, build and optimise Retrieval‑Augmented Generation pipelines and agentic workflows that leverage large language models on proprietary, domain‑specific knowledge bases within the healthcare sector.

Key responsibilities

• Design, build and optimise Retrieval‑Augmented Generation (RAG) pipelines and agentic workflows.
• Fine‑tune open‑source and proprietary foundation models (e.g., using LoRA, QLoRA) for tasks such as medical clinical summarisation, text extraction and entity recognition.
• Develop, train and validate deep‑learning models (transformers, CNNs, sequence models) for unstructured text, medical imaging or physiological time‑series data.
• Build and scale pipelines for feature extraction, semantic search and multimodal applications.
• Wrap machine‑learning and generative‑AI models into high‑performance REST or gRPC APIs using FastAPI or Flask.
• Deploy models efficiently with inference engines such as vLLM, Hugging Face TGI or Triton Inference Server to minimise latency and optimise GPU memory utilisation.

Required profile

• Bachelor’s degree in Computer Science, Software Engineering, Statistics or a highly quantitative discipline.
• Master’s or PhD in Computer Science, Artificial Intelligence, Deep Learning, Data Science or a related quantitative field.
• At least 1 year of professional experience as an AI Engineer, NLP/ML Engineer or Deep Learning Specialist.
• Prior experience in healthcare, clinical informatics or pharmaceutical environments is preferred but not mandatory.

Required skills

• Python
• Hugging Face (Transformers, PEFT)
• LangChain, LlamaIndex, LangGraph
• Vector databases: Chroma, PGVector, Qdrant
• Model deployment and serving: vLLM, Triton, FastAPI, Flask, Docker, Git
• BI and model visualisation: Streamlit, Gradio, Plotly, Tableau (preferred)
• Cloud platforms: Azure ML, AWS SageMaker