What project we have for you

About the Tour Planning Product

Join us in tackling one of the most fascinating challenges in logistics: the Vehicle Routing Problem (VRP).

Our client’s Tour Planning solution is the engine behind multi-vehicle route optimization, empowering businesses to design smarter, faster, and more driver-friendly tours.

They harness precise and up-to-date map data, real-time traffic insights, road restrictions, and driver preferences to craft tours that are both efficient and practical. The mission is to transform complexity into clarity – delivering solutions that reduce travel time, cut costs, and keep logistics operations running smoothly.

Their algorithms factor in every critical detail – driver preferences, delivery time windows, vehicle capacities, and compliance requirements – ensuring that every plan is efficient and meets all constraints. This holistic approach drives cost savings, delivery accuracy, and driver satisfaction while supporting sustainable and compliant operations.

If you’re passionate about solving real-world problems at scale, developing sophisticated algorithms, and pushing the boundaries of logistics technology, this opportunity is for you.

About the Team

You will join a diverse, passionate team of experts focused on solving complex logistics challenges and delivering impactful solutions. The team values quality, innovation, and continuous improvement.

The tech stack includes Rust, Kotlin, Python, AWS, Docker, Kubernetes, and Terraform – empowering the development of scalable, high-performance systems.

As a key contributor, you will advocate for end users, define quality standards, and help deliver solutions that make a real difference.

What you will do

Position Focus:

• Shift from classic test automation to data-driven evaluation and algorithm quality assurance.
• Build and maintain end-to-end evaluation pipelines for optimization outputs, define robust statistical quality metrics, and implement monitoring and alerting for production algorithms.
• Combine software engineering-in-test practices with deep data-analysis skills to validate complex optimization systems and ensure reliable, measurable product behavior.
• Work closely with engineering and product teams to operationalize validation, improve algorithm robustness, and drive continuous improvement of the Tour Planning product.

In this role, you will:

• Design, build, and maintain end-to-end evaluation pipelines for algorithmic outputs (ingest, transform, score, aggregate, visualize).
• Define and own KPI-based validation frameworks for optimization performance (distance/cost reduction, SLA adherence, load balancing, constraint violations, solution feasibility).
• Implement statistical and quantitative validation methods to assess algorithm quality.
• Develop dashboards and monitoring systems to track model/algorithm health, performance trends, and anomalies; create alerts for significant quality degradations.
• Perform root-cause analyses on detected issues: analyze SHAP/feature attributions, distribution shifts, data pipeline problems, and model behavior changes.
• Collaborate with engineers to instrument production systems, integrate evaluation hooks, and operationalize data-driven rollouts and canary tests.
• Produce clear, actionable reports and visualizations for product and engineering stakeholders; recommend mitigations and validation-driven improvements.
• Assist in advancing validation methodology beyond rule-based checks: introduce probabilistic metrics, uncertainty quantification, and robust statistical controls.
• Collaborate with engineering teams on best practices for data-driven validation and monitoring.

What you need for this

• Bachelor’s or Master’s degree in Data Science, Statistics, Computer Science, Applied Mathematics, Operations Research, or a related field — or equivalent practical experience.
• 3–5+ years of hands-on experience in data science, algorithm evaluation, ML model validation, or analytics within a product/engineering team.
• Strong Python proficiency for data engineering, analysis, scripting, and automation (comfortable with NumPy, Pandas, scikit-learn or equivalent).
• Solid statistical foundations: hypothesis testing, confidence intervals, bias/variance trade-off, calibration, and A/B testing principles.
• Proven ability to design and implement end-to-end evaluation pipelines and translate results into actionable product requirements.
• Experience working with large datasets; familiarity with ETL/feature pipelines and batch or near-real-time data processing.
• Demonstrable experience building dashboards and monitoring systems to track model/algorithm quality and key performance indicators.
• Strong communication skills and the ability to present quantitative findings clearly to engineering and product stakeholders.

Required skills:

• Python for data analysis and automation (NumPy, Pandas, scikit-learn or equivalent).
• Statistical analysis and applied inference (hypothesis testing, confidence intervals).
• Design and implementation of evaluation frameworks: metrics definition, backtesting strategies, cross-validation, and error analysis.
• Experience validating algorithmic outputs quantitatively (rather than rule-based assertions) and designing KPI-based validation for optimization systems (e.g., distance reduction, SLA adherence, constraint violations).
• Hands-on experience with large datasets (data cleaning, aggregation, ETL).
• Experience creating visualizations and dashboards to communicate model/algorithm quality (Plotly/matplotlib/seaborn).
• Ability to program full pipelines: data ingestion → processing → evaluation → reporting/alerting.
• Collaborative mindset: work effectively with developers, QA, and product managers; translate analyses into practical recommendations.

Preferred skills:

• Prior experience validating optimization algorithms, combinatorial solvers, or routing/VRP-related systems; exposure to logistics/location-based products.
• Experience with experimentation frameworks and causal inference basics for evaluating changes in algorithms or heuristics.
• Cloud and deployment familiarity (AWS, Docker, Kubernetes) and experience deploying data pipelines or monitoring services.
• Experience with interactive visualization/dashboard frameworks (Plotly/Dash, Streamlit, Tableau, Power BI).
• Background in operations research, applied mathematics, or statistics.
• Exposure to GIS data, mapping workflows, or spatial analysis.
• Knowledge of Rust or Kotlin (useful for cross-team collaboration) — not required.

Skills

• DataAnalyst
• ML
• Python