Junior Data Scientist (f/m/n)

InPost

1d • Remote

About The Position

You’ll join the Forecasting Domain within our Data & AI division as a Junior Data Scientist. Our team predicts parcel volumes and operational demand across multiple European markets - forecasts that drive planning, capacity and decisions all the way up to C-level. This is a role built for someone at the start of their career: you’ll learn directly from experienced data scientists, contribute to real forecasting models from day one, and grow along a clear path from Junior toward Senior and beyond. We care more about how you think than how many years you’ve worked. Tech stack : Python (Pandas, NumPy, Scikit-learn), SQL & data warehouses, PySpark & distributed processing, Databricks, Cloud platforms (Azure / GCP / AWS).

Requirements

• Higher education in progress or completed (Bachelor’s or Master’s) in computer science, statistics, mathematics, physics, econometrics or a related field
• Around a year of first commercial / internship experience in data analysis or data science - or an equally strong record of documented academic, research or competition participation
• Good knowledge of Python for data workflows (Pandas, NumPy, Scikit-learn)
• Practical SQL skills for querying relational databases
• Solid grounding in data cleaning, wrangling and exploratory data analysis (EDA), and a good understanding of basic statistics
• Familiarity with core ML methodologies (regression, classification), including evaluation metrics and cross-validation
• Ability to visualise and communicate insights clearly (e.g. Matplotlib, Plotly), with focus on storytelling and clarity
• English at B2 level or higher
• Proficiency in the use of LLM-Agentic technology in software development: Claude Code, Cursor, OpenAI Codex, etc.

Nice To Haves

• A strong track record in data science / ML competitions (Kaggle and similar), olympiads or hackathons
• Documented academic or personal projects in data analysis or machine learning — a thesis, research, publications or a solid github portfolio
• Exposure to time series or forecasting methods (e.g. ARIMA / classical statistical models, gradient boosting, or modern forecasting approaches)
• Familiarity with PySpark or other big-data tools
• A basic understanding of cloud platforms (e.g. AWS, GCP, Azure) and simple data pipelines (Airflow, dbt)
• Experience building dashboards and reports (Streamlit, Dash, Power BI)
• Exposure to containerisation and experiment tracking (Docker, MLflow)
• Reproducible-workflow habits: notebooks, Git, clean code and clear documentation

Responsibilities

• Run end-to-end forecasting analyses on real business problems - from data preparation and feature engineering through to modelling and turning results into clear, actionable recommendations
• Build and evaluate time series and machine learning forecasting models, validating them through rigorous testing and iterative improvement
• Write clean, well-structured code and take part in code reviews to keep our standards high and share knowledge
• Take ownership of your tasks: estimate your work, communicate progress, and flag issues early to deliver on time
• Support the full lifecycle of our forecasting products, helping maintain models in production and contributing to handovers
• Keep learning - deepening your technical foundations and forecasting expertise through on-the-job work and close collaboration with the team

Benefits

• Access to e-learning platforms- eTutor , GoodHabitz , Data Camp , and more.
• MultiSport+ card
• private healthcare
• group insurance
• External and internal growth opportunities - conferences , trainings , workshops .
• Chances to broaden your skill set and acquire new competencies through daily work, challenging projects, and training activities.

What This Job Offers

• Job Type: Full-time
• Career Level: Entry Level
• Education Level: Associate degree