Deep Learning Engineer

Thames Valley ICB; Stanford Dingley; On-site; GBP 65,000 - 90,000; Full time

Job summary

Thames Valley Integrated Care Board is seeking a Deep Learning Engineer to design, develop and deploy deep learning models that support future disease progression, predictive case finding and population needs across the Connected Care ecosystem. You will work with clinical colleagues to validate models before deployment and ensure outputs feed directly into clinical records and care workflows.

You will apply NLP where relevant, implement monitoring and explainability, and uphold information

Qualifications

• Hands-on experience building deep learning models for clinical outcomes.
• Experience with MLOps and AI deployment.
• Knowledge of NHS information governance and clinical safety standards.

Responsibilities

• Design, validate and deploy DL models for disease progression and predictive case finding.
• Collaborate with clinical teams to ensure safety and relevance.
• Integrate models with population health systems and care workflows.
• Establish model monitoring, explainability and drift detection.

Skills

PyTorch

TensorFlow

Azure Machine Learning

Tools

PyTorch

TensorFlow

Azure Machine Learning

Job description

Designing, developing and deploying deep learning models for future disease progression, predictive case finding and population needs, using frameworks such as PyTorch, TensorFlow and Azure Machine Learning.

Working closely with clinical colleagues to validate models, ensuring they are safe, trusted and clinically relevant before deployment.

Integrating models with our population health system and data integration platform so that predictive insights reach clinical records and care workflows.

Implementing model monitoring, validation, explainability and drift detection approaches.

Building natural language processing (NLP) models to derive insights from clinical and operational text data where relevant.

Providing technical leadership on model architecture, MLOps and AI deployment approaches.

Ensuring compliance with NHS standards, information governance, clinical safety (DCB0129/DCB0160) and responsible AI principles. At our Organisation, our selection process ensures we recruit candidates with the right skills and values. We monitor AI use in applications and remain alert to misuse that misrepresents abilities.

Thames Valley Integrated Care Board is looking for a Deep Learning Engineer to apply deep learning and machine learning to direct care applications across our Connected Care ecosystem.

Connected Care is Thames Valley's expert-led, integrated healthcare-data ecosystem. Since 2016 it has grown from a simple shared care record into a powerful intelligence tool enabling provider collaboration and proactive, direct patient care across the Thames Valley system. This is a direct care function, not a commissioning role.

Your focus will be on future disease progression, predictive case finding and population needs -- building models that help clinicians and care teams identify risk earlier and target interventions more effectively. You'll create, validate and deploy these models working closely with clinical colleagues, and integrate them with our population health system and data integration platform so that model outputs feed directly back into the information clinicians see.

You'll be applying deep learning directly to patient outcomes -- helping clinicians spot disease progression and case-find earlier -- as part of one of the largest Connected Care programmes in the country, supporting 2.5 million people across Buckinghamshire, Oxfordshire and Berkshire.

We value and promote diversity and are committed to equality of opportunity for all. We believe that the best employers are those that reflect the communities they serve. We want to increase the diversity of our NHS leadership and particularly encourage applications from women, people from Black, Asian and Minority Ethnic communities, LGBT communities, younger candidates and from people with lived experience of disability, who we know are all under-represented in these important roles. We are committed to delivering a trustworthy, flexible and responsible staff culture.