Lead Data Scientist - Python - SC & NPPV3 Cleared

SR2 REC LTD; Greater London; On-site; GBP 90,000 - 120,000; Full time

Job summary

SR2 REC LTD is seeking an experienced Lead Data Scientist to own data matching and entity resolution within a major public sector data transformation programme. The role is hands-on and leadership-focused, delivering scalable, explainable solutions for large datasets.

You will drive methodologies for deterministic, probabilistic and fuzzy matching, and work with data engineers to move solutions into production, coordinating with senior stakeholders to ensure measurable improvements in data

Qualifications

• Active SC & NPPV3 clearance.
• Senior/Lead data scientist experience.
• Experience with entity resolution, fuzzy matching, record linkage or deduplication.
• Advanced Python, SQL and statistical analysis skills.
• Experience handling large, complex datasets.
• Strong data quality, model evaluation and explainability knowledge.
• Experience delivering production-ready data science solutions.

Responsibilities

• Lead the development of entity resolution, record linkage and data matching methodologies.
• Design deterministic, probabilistic and fuzzy matching approaches.
• Analyse data quality, inconsistencies and matching confidence.
• Develop and evaluate algorithms using Python, SQL and statistical techniques.
• Define performance measures including precision, recall and false-positive rates.
• Collaborate with data engineers to transition proofs of concept into production.
• Provide technical leadership and engage with senior stakeholders.

Skills

Python

SQL

Statistical analysis

Data quality

Model evaluation

Explainability

Production-ready solutions

Tools

AWS

Redshift

Glue

Job description

Lead Data Scientist - Python - SC & NPPV3 Cleared

We\'re looking for an experienced Lead Data Scientist to take ownership of data matching and entity resolution approaches within a complex public sector data transformation programme.

This is a hands-on leadership opportunity focused on developing reliable, explainable and scalable approaches to analysing and linking large datasets.

Key responsibilities:

• Lead the development of entity resolution, record linkage and data matching methodologies.
• Design deterministic, probabilistic and fuzzy matching approaches.
• Analyse data quality, inconsistencies and matching confidence.
• Develop and evaluate algorithms using Python, SQL and statistical techniques.
• Define performance measures including precision, recall and false-positive rates.
• Work closely with data engineers to transition solutions from proof of concept into production.
• Provide technical leadership and collaborate with senior stakeholders.

Essential experience:

• Active SC & NPPV3 clearance
• Strong background as a Senior or Lead Data Scientist.
• Proven experience in entity resolution, fuzzy matching, record linkage or deduplication.
• Advanced Python, SQL and statistical analysis skills.
• Experience processing large, complex and imperfect datasets.
• Strong understanding of data quality, model evaluation and explainability.
• Experience delivering production-ready data science solutions.

AWS, Redshift, Glue and government programme experience would be advantageous.