Data Scientist, Domain-Aware Hybrid Search & Discovery

Allegro; Poznań; Hybrid; PLN 180,000 - 260,000; Full time

Benefits offered by this job

Flexible hybrid hours

Annual bonus

30 days remote work

MacBook Pro or Dell laptop

Fringe benefits cafeteria plan

English classes

Training budget

Volunteer day

Social events

Well-equipped offices

Job summary

Allegro is hiring a mid-level Data Scientist to advance a Domain-Aware Hybrid Search. You’ll build and deploy models for predictive and discovery tasks, collaborate with cross-functional teams, and help move our Central Query Understanding forward.

You will work with Python, large-scale datasets on Google Cloud, and modern ML techniques while aligning with business processes and GenAI challenges. Hybrid work and a busy benefits program await.

Qualifications

• Have a degree strongly related to statistical/mathematical modeling.
• Possess at least 2 years of experience in data analysis and building machine learning solutions that have been released to production.
• Have a strong understanding of statistical and machine learning methods, specifically for forecasting and decision tree-based algorithms.
• Are proficient in Python and efficient in using basic development tools.
• Can process massive datasets (terabytes of data) using Google Cloud Platform solutions, working with tabular, spatial, natural language, image, and time-series data.
• Know English at a B2 level and Polish at a C1 level.
• Demonstrate core competencies in Analytical Thinking, Learning Agility, Cooperation, and Continuous Improvement & Innovation.

Responsibilities

• Designing, developing, and deploying models that solve complex business problems, including predictive, segmentation, forecasting, and recommendation models.
• Developing query-to-category and query-to-product matching models to enhance the search experience.
• Building internal AI Engineering competence, including fine-tuning small, efficient models.
• Taking an active part in all Data Science project phases: from problem formulation and data exploration to modeling, automation, release, and monitoring.
• Using a wide range of model types, including boosting, Bayesian methods, causal inference, optimization methods, deep learning, and forecasting models.
• Collaborating across teams, partnering with business stakeholders, analytics, and data engineering teams on experiment setup and deployment.
• Ensuring models reflect business processes' specificity and staying up-to-date with GenAI challenges.

Skills

Python

Data analysis

Machine learning

Forecasting

Decision trees

Google Cloud Platform

Education

Degree in statistics/mathematical modeling

Tools

Kubernetes

Docker

Consul

GitHub

GitHub Actions

Job description

Allegro is hiring a mid-level Data Scientist to advance a Domain-Aware Hybrid Search. You’ll build and deploy models for predictive and discovery tasks, collaborate with cross-functional teams, and help move our Central Query Understanding forward.

You will work with Python, large-scale datasets on Google Cloud, and modern ML techniques while aligning with business processes and GenAI challenges. Hybrid work and a busy benefits program await.