Machine Learning Engineer

Machine Learning Engineer (Copy)

sennder HQ Berlin

Machine Learning

In office

Full-time

sennder is redefining road logistics. As Europe’s leading digital freight forwarder, we are building a smarter, faster, and more sustainable future for freight, powered by a single, unified platform that already runs our entire business. We are moving from a decade of growth through acquisition to a company that is outcome-driven, outward-focused, and AI-native by design.

Logistics is one of the best possible use cases for AI, and unlike most of our peers, we own the full loop: the platform, the operations, and the data connecting them. That closed feedback loop is a compounding advantage most competitors can’t replicate. This role exists to turn that advantage into sennder’s sharpest edge in margin, cost, and service, because AI will give us that edge if we lead, or become a risk if we lag.

As a Machine Learning Engineer, you will join our highly talented ML team. This is an applied machine learning role focused on highly innovative, research-oriented topics. You will work on a diverse portfolio of high-impact projects, ranging from optimizing our established Recommendation engine & Pricing engine to building greenfield solutions. This role can be based out of our Berlin, Barcelona or Amsterdam office.

To succeed, this role demands a strong focus on deep Data Science and statistical exploration (roughly 70% of your scope), paired with the foundational Machine Learning Engineering skills (~30%) required to transition prototypes into production-ready models. You will not just be implementing technical specifications; you will sit directly with end-users, operators, and Product Managers to deeply understand their workflows, granting you real decision‑making power over the product's direction.

You are expected to have a holistic approach to project deployment, acting as an end‑to‑end ML Engineer and taking full ownership from "Light MVP" R&D to production deployment.

• Pricing Engine Optimization: Develop and iterate on bid estimation algorithms and margin‑optimization models to power our dynamic pricing engine, directly driving company profitability.
• Carrier Forecasting: Build robust predictive models to forecast carrier behavior and market capacity, enabling our operational teams to secure the right trucks at the right price before the market shifts.
• Recommender Systems: Maintain and improve our existing recommender systems to seamlessly support our operational teams' day‑to‑day efficiency.
• Industry Innovation & Applied ML: Explore and validate new areas where machine learning can solve fundamental logistics challenges (such as freight routing and network optimization), turning open‑ended industry problems into scalable, data‑driven solutions.
• Product Discovery & Ideation: Partner closely with Product Managers to drive continuous product discovery, translating ambiguous operational pain points into clear, outcome‑driven ML hypotheses and rapid prototypes.
• AI & LLM Integration: Leverage foundational models and AI agents both as daily accelerators for your own engineering workflows and as core components to build new internal products. We expect you to pragmatically evaluate trade‑offs and always choose the right solution for the right problem—whether that is an LLM, a traditional ML model, or a simple heuristic.
• Platform
  
  Collaboration:
  
  Partner with our Data & AI Platform (MLOps) team to utilize and deploy models via our internal ML infrastructure. You will act as a key customer of this platform, providing continuous feedback and contributions to shape our global engineering standards.
• End‑to‑End Execution: Adopt a holistic approach to project deployment, maintaining an end‑to‑end attitude that covers the entire lifecycle from initial R&D and prototyping all the way through to production release and monitoring.

• Experience: 5+ years of hands‑on experience in Data Science or Machine Learning Engineering.
• Data Science Fundamentals: Strong foundation in statistical analysis, hypothesis testing, and deep data exploration to validate assumptions and commercial viability before building…