Description:
Our client is revolutionising healthcare for millions of patients worldwide. With over 20 years of proprietary wearable technology and clinically relevant signals, they are redefining primary care while helping people live happier, healthier, and longer lives. They are looking for a GenAI Engineer to join their team in London. In this role, you will design, build, and optimise RAG pipelines that combine large language models (LLMs) with domain-specific retrieval systems, enabling natural language understanding and reasoning over patient data, clinical guidelines, and health records.
As a GenAI Engineer, your work will be at the heart of our client's mission to redefine healthcare. You'll be responsible for designing and implementing RAG architectures that leverage both open-source and potentially proprietary Large Language Models (LLMs). Your expertise will be crucial in building retrieval pipelines over a variety of health data types. You'll also develop indexing strategies using cutting-edge vector databases and embedding models. Your role will involve integrating these outputs into user-facing applications while ensuring the information provided is reliable, grounded, and respects privacy regulations. Collaborating with product, clinical, and data science teams will be key as you fine-tune prompts, evaluate responses, and continually improve model performance. Additionally, you'll contribute to creating an infrastructure that supports scalable GenAI deployments and efficient model versioning.
- Design and implement RAG architectures using open-source and potentially proprietary LLMs.
- Build and maintain retrieval pipelines over structured and unstructured health data.
- Develop indexing strategies using vector databases and embedding models.
- Integrate RAG outputs into user-facing applications, ensuring responses are grounded, reliable, and privacy-compliant.
- Work closely with product, clinical, and data science teams to fine-tune prompts, evaluate responses, and iterate on model performance.
- Build evaluation pipelines for factuality, relevance, and safety using synthetic and real-world datasets.
- Contribute to infrastructure for scalable GenAI deployments and model versioning.
- Stay up to date with the latest research in GenAI and health tech applications of LLMs.
What you bring:
As the ideal candidate for the GenAI Engineer role, you bring a wealth of experience in machine learning and NLP roles. Your strong proficiency in Python, deep learning frameworks such as PyTorch or TensorFlow, and GenAI libraries will be essential to your success in this role. You have hands-on experience with vector search, embedding models, and retrieval pipelines. Your familiarity with prompt engineering, prompt tuning, and evaluation of generative model outputs sets you apart. Experience working with healthcare or sensitive data is crucial, as is an understanding of HIPAA/GDPR compliance. Your strong problem-solving skills will be invaluable in our fast-paced environment.
- 3+ years of experience working in machine learning / NLP roles.
- Strong proficiency in Python, deep learning frameworks (PyTorch or TensorFlow), and GenAI libraries.
- Hands-on experience with vector search, embedding models, and retrieval pipelines.
- Familiarity with prompt engineering, prompt tuning, and evaluation of generative model outputs.
- Experience working with healthcare or sensitive data (HIPAA/GDPR compliance awareness).
- Strong problem-solving skills.
- Bonus: Experience with MLOps, Kubernetes, AWS/GCP, and deploying models in production.
Robert Walters Operations Limited is an employment business and employment agency and welcomes applications from all candidates
