Medical Doctor with SNOMED Coding Experience (UK)

Description

We are seeking qualified medical doctors to annotate and code clinical documents with SNOMED CT, with a focus on accuracy and consistency against detailed coding guidelines.

You will work asynchronously on a dedicated annotation platform, coding de-identified clinical notes and documentation including discharge summaries, lab results and progress notes against SNOMED CT concepts to support the development of clinical AI platforms.

This is a remote, flexible and short-term project.

Key Responsibilities

• Structured Annotation: Identify clinically relevant concepts across discharge summaries, lab results and prognosis notes, and map them to the correct SNOMED CT codes on a dedicated platform.

• Guideline Application: Work to a coding guideline covering hierarchy scope, negation, medication scope, section-level inclusions and compound coding, applied consistently across a large volume of documents.

• Edge Case Handling: Flag ambiguous or contested cases with a short rationale so guidance can be refined.

• Quality Review: Participate in adjudication rounds to resolve disagreements and reach a consensus code set.

Requirements

License: GMC Registered Doctor based in the UK

Experience: Minimum 1–2 years of clinical practice, with SNOMED CT coding or clinical terminology experience.

Knowledge: Strong grounding in clinical documentation, terminology and coding conventions.

Attention to detail: Proven accuracy and consistency in coding or clinical review work.

Technical proficiency: Comfortable using structured annotation tools and digital platforms.

Language: Native or near-native written English.

Legal Status

You will have the right to work in your country of residence.

You will work as an independent contractor.

Benefits

• Flexible Work Arrangements: Part-time, remote and fully asynchronous.

• Competitive Compensation: Hourly rate, paid weekly

• Professional Development: Hands-on experience in clinical AI development and terminology work, shaping how AI systems interpret clinical records and assign medical codes.