Data Scientist – Warsaw

QED is a tech company focused on public health and food security in Sub-Saharan Africa. They build digital infrastructure and AI for aid and scientific inquiry, including nutrient analysis of crops, soils, and foods, and surveillance of HIV and malaria at national scale in multiple African countries. Their funding comes from philanthropic and governmental organizations such as the Gates Foundation, the Polish Ministry of Agriculture, EU funding programmes, and the Global Fund.

Technical:

• Proficiency with core ideas in statistics
• Formal academic studies in statistics, data science, or software engineering with practical experience analyzing real-world datasets
• Ability to use computer programming to wrangle, inspect, and analyze statistical data
• Proficiency with git and Python-based programming environments, preferably with CI/CD
• Practical proficiency with traditional statistical techniques (regression, hypothesis testing, survey design, time series, RCTs) and modern machine learning methods (decision trees, boosting, neural networks)
• Tenacity and curiosity to acquire domain expertise in biology, chemistry, agronomy

General:

• Working proficiency (≥C1) in English speaking and reading, capable of typing ≥45 words per minute
• Logical reasoning and clear oral and written communication
• Willingness and interest in working with people from other cultures with emotional resilience and social intelligence
• Willingness to engage hands-on with work
• Genuine care about the work performed

Nice to have:

• Prior experience with spectroscopy (Vis/NIR/MIR) and chemometrics
• Understanding of spectroscopy physics
• Experience with calibration transfer, drift monitoring, or multi-instrument datasets
• Domain familiarity with food chemistry, agriculture, grain quality, soil/plant analysis, lab reference methods
• Interest in sustainable development goals related to agriculture, climate change, public health, and assisting developing countries

• Build and improve regression models for spectroscopic data (e.g., PLSR, SVR, Extra Trees)
• Plan sampling strategies and real-world experimental design with a strong statistical mindset
• Design robust training and evaluation pipelines including preprocessing, feature engineering, hyperparameter tuning, and cross-validation
• Apply chemometrics best practices to spectral data (baseline/scatter effects, derivatives, outliers, drift)
• Diagnose model failures and data issues and propose fixes
• Construct dashboards and reports to present and visualize data analytics
• Collaborate with engineering and product teams to package and deploy models
• Assist in communication with scientific institutes, companies, and researchers
• Collaborate with governmental, medical, agronomic, and computer science teams on research papers and impact reports