Senior Data Scientist

SR2; City Of London; On-site; GBP 120,000 - 134,000; Full time

Job summary

SR2 is seeking a Senior Data Scientist with active SC clearance to join a major government programme in London. You will work on a large-scale data matching engine, improving accuracy and performance across systems while refining matching rules and data-driven insights.

Key tech includes Python (pandas, NumPy, scikit-learn), SQL, Elasticsearch, Kubernetes, Docker, and related data-processing tools. Onsite presence is required two days per week with ASAP start.

Qualifications

• Entity resolution, record linkage or fuzzy matching experience.
• Strong Python experience, including pandas, NumPy and scikit-learn.
• Solid SQL skills and experience working with large datasets.
• Experience with Elasticsearch, Kubernetes and Docker.
• Understanding of precision, recall and false-positive optimisation.
• Exposure to Kafka, AWS, PostgreSQL, Bash, Jenkins or Ansible would be beneficial.
• Previous experience in government, defence, security or identity matching environments is advantageous.

Responsibilities

• Analyse and optimise entity resolution and data matching performance.
• Refine, test and implement matching rules using data-driven insights.
• Improve matching accuracy, precision and recall.
• Work closely with engineering teams to deliver improvements into production.
• Support performance testing and ongoing optimisation.

Skills

Entity resolution

Fuzzy matching

Python (pandas, NumPy, scikit-learn)

SQL

Elasticsearch

Kubernetes

Docker

Precision/recall optimization

Kafka

AWS

PostgreSQL

Bash

Jenkins

Ansible

Tools

Elasticsearch

Kubernetes

Docker

Kafka

AWS

PostgreSQL

Bash

Jenkins

Ansible

Job description

Senior Data Scientist - SC Cleared
Location: London - 2 days per week onsite
Rate: £650 - £725 per day (Inside IR35)
Contract: 6 months+, long term programme (3 years)
Start: ASAP within 1 month
Clearance: Active SC Clearance required

The Opportunity

We're looking for an experienced Data Scientist to join a major government programme, working on a large-scale data matching engine used to identify potential national security risks.

You'll focus on improving the accuracy and performance of an existing matching engine, analysing how personal data is matched across multiple systems and refining the rules to reduce false positives and improve operational efficiency.

Key Responsibilities

• Analyse and optimise entity resolution and data matching performance.
• Refine, test and implement matching rules using data-driven insights.
• Improve matching accuracy, precision and recall.
• Work closely with engineering teams to deliver improvements into production.
• Support performance testing and ongoing optimisation.

Key Skills & Experience

• Entity resolution, record linkage or fuzzy matching experience.
• Strong Python experience, including pandas, NumPy and scikit-learn.
• Solid SQL skills and experience working with large datasets.
• Experience with Elasticsearch, Kubernetes and Docker.
• Understanding of precision, recall and false-positive optimisation.
• Exposure to Kafka, AWS, PostgreSQL, Bash, Jenkins or Ansible would be beneficial.
• Previous experience in government, defence, security or identity matching environments is advantageous.

Security Clearance: Candidates must hold active SC clearance.