Who We Are

Airmee is a rapidly scaling last-mile logistics platform, backed by Bonnier Capital and other leading investors. We were founded to build the best and most sustainable delivery experience on the market.

Today, we are Sweden’s largest player in home deliveries and one of the few last-mile companies combining strong growth with profitability. In 2024, we reached SEK 362M in revenue, and in 2025 surpassed SEK 600M, driven by a tech-enabled platform. We’re now entering our next chapter: scaling smarter, strengthening our operational engine, and continuing to raise the standard for last-mile logistics in the Nordics.

Role Overview

As lead data scientist, you will focus on large-scale route optimization in a production environment, where decisions directly impact cost, delivery performance, and operational efficiency.

You will design, implement, and continuously improve optimization systems that operate under real-world constraints (scale, latency, imperfect data, changing conditions). The role requires both strong operations research fundamentals and the ability to take solutions from prototype to production in close collaboration with engineering.

A key part of the role is experiment-driven development - systematically validating improvements and ensuring that changes lead to measurable business impact.

Responsibilities

1. Develop and improve routing and scheduling algorithms (e.g. VRP) for large-scale, operations

2. Formulate optimization problems based on operational constraints and business objectives

3. Build solutions that balance optimality, scalability, and runtime constraints

4. Take models from prototype to production, working closely with engineering on integration & reliability

5. Design and run controlled experiments (A/B tests, simulations) to evaluate impact of changes in close collaboration with superuser from business side

6. Define success metrics to ensure improvements are statistically and operationally validated

7. Own and prioritize an optimization roadmap aligned with business goals

8. Collaborate with operations, engineering, and business stakeholders to ensure solutions are practical and adopted

Problem Context

1. High-volume routing with tens of thousands of deliveries & tight constraints

2. Dynamic and stochastic environments (e.g., delays, demand variability)

3. Trade-offs between cost, speed, & service quality

4. Need for both planning optimization & real-time adjustments

Requirements

Must-Have

1. Strong background in operations research / optimization

2. Proven experience working on routing or logistics problems at scale

3. Strong Python skills

4. Experience taking models from research or prototype into production systems

5. Experience designing and evaluating experiments (A/B testing, simulations, or similar)

6. Ability to work closely with engineering on system integration and performance considerations

7. Strong problem formulation skills - translating business problems into solvable models

Nice-to-Have

1. Experience with real-time or near real-time optimization systems

2. Familiarity with common routing solvers and frameworks (and their limitations)

3. Data engineering knowledge (data pipelines, data quality, infrastructure)

4. Experience in high-scale operational environments

5. Experience building teams 

How You Will Work

1. Operate as a hands-on contributor, responsible for both modeling and implementation

2. Work in tight collaboration with engineering, operations, and business teams

3. Own problems end-to-end, from definition through deployment and iteration

4. Use experiment-driven methods to guide improvements and prioritization

Success Criteria

1. Optimization models are deployed, stable, and actively used in production

2. Improvements are validated through experiments and tied to business KPIs

3. Measurable impact on cost efficiency, delivery performance, and utilization

4. Systems scale reliably with increasing volume and complexity

5. A clear foundation is established for a future Data Science team

Role Evolution

This role starts as a senior individual contributor position and is expected to evolve into building and leading a Data Science / Optimization team as the function grows.

Practicalities

Location: Stockholm

Reports to: CTO

Scope: Hands-on individual contributor with a clear path to building and leading a Data Science team