Data Analytics Intern: Time Series & Anomaly Detection

WOAH; Paris; On-site; EUR 6,800 - 9,200; Full time

Job summary

WOAH HQ in Paris is offering an internship for a Data Analyst to develop an anomaly detection system using WAHIS official data and EIOS open sources. You will build time series, benchmark algorithms, and help design dashboards and automated alerts for internal WOAH use.

The role emphasizes reproducible code, documentation, and the ability to work with official data streams to detect anomalies across diseases, contributing to an early warning workflow.

Qualifications

• Education: master’s degree in Data Science, Biostatistics, Statistics, Applied Mathematics, or Epidemiology.
• Experience: not required; coursework or academic project acceptable.
• Basic knowledge of time series analysis and reproducible analytic coding.

Responsibilities

• Build time series from WAHIS and EIOS for each disease and country/region.
• Benchmark anomaly detection algorithms across WAHIS and EIOS data.
• Evaluate performance against reported events (early warning, peak, post-peak).
• Compare signals from EIOS and WAHIS and design integrated alerts.
• Develop a reproducible pipeline and dashboards for WOAH use.

Skills

Programming in R and/or Python

SQL querying

Git version control

Reproducible reporting (Quarto or R MD

Dashboard development (Shiny, Dash, BI

Automated task scheduling

Data management practices

Code documentation and structuring

Education

Master’s degree in Data Science, Biostatistics, Statistics, Applied Mathematics, or Epidemiology

Tools

SQL

Git

Job description

WOAH HQ in Paris is offering an internship for a Data Analyst to develop an anomaly detection system using WAHIS official data and EIOS open sources. You will build time series, benchmark algorithms, and help design dashboards and automated alerts for internal WOAH use.

The role emphasizes reproducible code, documentation, and the ability to work with official data streams to detect anomalies across diseases, contributing to an early warning workflow.