Lead Data Science Engineer

Charger Logistics Inc. is a leading asset-based transportation company with operations across North America. With more than 20 years of experience delivering innovative logistics solutions, Charger Logistics has evolved into a world-class transport provider and continues to expand its footprint.

We are deeply committed to our people, investing in their development by fostering an environment where learning, growth, and career advancement are encouraged. As an entrepreneurial organization, we value initiative and actively support new ideas and forward-thinking strategies.

We are currently looking for a senior, hands-on Lead Data Science Engineer to join our team in Brampton, Ontario. This role will lead the design and implementation of large-scale machine learning and AI systems for fleet analytics and logistics optimization. The position focuses on production-grade ML, real-time streaming analytics, and AI-driven decision systems built on Google Cloud (Vertex AI, BigQuery), Kafka, and RisingWave.

In this role, you will architect, develop, and scale advanced ML and AI solutions supporting real-time fleet optimization, predictive maintenance, anomaly detection, and intelligent decision-making. This is a deeply technical data science and ML engineering role, tackling complex logistics and telematics challenges using cloud-native and streaming technologies.

As the technical lead for ML initiatives, you will own system architecture, model strategy, and production deployments, while working closely with product, engineering, and DevOps teams to deliver impactful, scalable solutions.

Responsibilities:

• Architect, build, and deploy production-grade machine learning and AI systems for fleet optimization, including route optimization, ETA prediction, fuel efficiency, capacity planning, and predictive maintenance.
• Develop advanced anomaly detection and forecasting models to identify trip deviations, fuel theft, vehicle health issues, driver behavior risks, and demand fluctuations using time-series and statistical techniques.
• Design and implement real-time and streaming ML systems with low-latency inference, feature engineering, and live anomaly detection using Kafka and RisingWave.
• Build adaptive, online learning and reinforcement learning models to enable dynamic routing and continuously optimized operational decisions.
• Integrate large language models (OpenAI, Google MCP, Ollama, Hugging Face) to deliver conversational analytics, automated insights, and AI-powered operational decision-support.
• Design and implement retrieval-augmented generation (RAG) systems for fleet intelligence, anomaly explanations, and knowledge discovery.
• Architect scalable ML platforms and MLOps workflows on Google Cloud using Vertex AI Pipelines, Feature Store, and Model Registry, supporting automated training, deployment, experimentation, monitoring, and drift detection.
• Ensure model explainability, governance, reliability, and cost-efficient production serving.
• Design and optimize analytical data models in BigQuery and AlloyDB PostgreSQL, and build scalable ETL/ELT pipelines for high-volume telematics and IoT data.
• Optimize data partitioning, clustering, and SQL-based feature engineering for performance at scale.
• Lead ML initiatives end-to-end, defining system architecture, standards, and best practices.
• Mentor data scientists and ML engineers, and communicate complex ML concepts effectively to both technical and non-technical stakeholders.

Requirements

• 5+ years of hands-on experience in data science and machine learning, delivering production-grade solutions.
• Expert-level proficiency in Python (3.9+), with strong software engineering, testing, and code quality practices.
• Deep hands-on experience with modern ML frameworks and libraries including scikit-learn, XGBoost, LightGBM, TensorFlow, and PyTorch.
• Strong expertise in anomaly detection, time-series forecasting, optimization, and applied statistical modeling.
• Proven experience deploying, monitoring, and experimenting with ML models in production environments, including A/B testing.
• 3+ years of hands-on experience with Google Cloud, including:
1. Vertex AI (model training, pipelines, deployment, and feature stores)
2. BigQuery (advanced SQL, performance tuning, and optimization)
3. Kafka and real-time streaming architectures
• Experience building and integrating LLM-based systems, including embeddings, vector search, and retrieval-augmented generation (RAG).
• Domain experience in logistics, fleet management, telematics, IoT, or similar large-scale operational data environments.
• Nice to Have
1. Experience with reinforcement learning, bandits, or advanced optimization techniques.
2. Computer vision experience for driver monitoring or dashcam analytics.
3. Exposure to geospatial or graph-based ML, including routing and GPS trajectory analysis.
4. Experience deploying ML solutions across multiple cloud platforms (AWS and/or Azure).
5. Background in sustainability initiatives, EV fleet optimization, or regulatory compliance.

Benefits

• Competitive Salary
• Healthcare Benefit Package
• Career Growth