ml engineer for real-time routing

Andersen is a global technology company that develops machine learning solutions and provides technology services for businesses across multiple industries. The project focuses on real-time routing optimization, ETA prediction, and large-scale geospatial data processing for a global investment management firm.

• Design and build ML models that refine routing engine ETA estimates using gradient-boosted trees, neural networks, and Transformer-based architectures;
• Develop traffic-estimation models from large-scale GPS data to generate road-level speeds and historical-traffic profiles;
• Implement map-matching and spatial aggregations for movement and speed data;
• Improve ETA calculation, smoothing, and rerouting logic across changing conditions;
• Translate routing and ETA goals into ML objectives, proxy metrics, non-functional requirements, and loss formulations;
• Lead end-to-end evaluation, including offline metrics and online experiments such as shadow tests and switchbacks;
• Partner with backend engineers to deploy models as low-latency production services meeting latency and throughput targets;
• Partner with product and operations teams to turn routing and traffic analysis into features and requirements;
• Own the production ML lifecycle, including serving, drift monitoring, and retraining pipelines.

• 5+ Years of Machine Learning experience, including 3+ years building and deploying deep learning models in production;
• Experience building regression, forecasting, or other supervised ML systems for real-world prediction problems;
• Strong Python skills and hands-on experience with PyTorch, Scikit-learn, Pandas, NumPy, and PySpark;
• Advanced SQL and distributed data processing experience;
• Experience with CatBoost, XGBoost, or LightGBM;
• Ability to design an ML system from scratch, from data analysis and processing through feature engineering and production model serving;
• Experience deploying low-latency ML services in production;
• Experience with MLOps, model monitoring, retraining pipelines, and lifecycle management;
• Upper-Intermediate English or above;
• Nice to have: expertise in ETA or travel-time prediction, traffic estimation, or routing-engine quality; experience with open-source routing engines such as Valhalla, OSRM, or GraphHopper; knowledge of map-matching, speed profiles, road-graph tiles, and historical traffic; experience with mapping, location, or geospatial products; experience building for developing markets with weak map and address data; experience with BigQuery or Databricks; distributed deep-learning training; relevant certifications.

• Fully remote work, office work, or a hybrid option is available;
• Professional, financial, and career growth opportunities;
• Mentoring and onboarding systems for each new employee;
• Opportunity to earn up to an additional 1,000 USD per month depending on expertise, included in the annual bonus;
• Access to the corporate training portal;
• Certification compensation, including AWS and PMP;
• Referral program;
• Private health insurance;
• Sports activity compensation;
• Corporate events and benefits, including parties, pizza days, PlayStation, fruits, coffee, snacks, and movies.