- Company Name
- Charger Logistics Inc.
- Job Title
- Senior Data Scientist
- Job Description
-
**Job Title:** Senior Data Scientist
**Role Summary:**
Lead end‑to‑end development of production‑grade machine learning systems for fleet analytics and logistics optimization on Google Cloud (Vertex AI, BigQuery), Kafka, and RisingWave. Drive real‑time decision systems, anomaly detection, predictive maintenance, and conversational AI solutions, while ensuring model reliability, explainability, and cost‑efficiency.
**Expectations:**
- 5+ years of hands‑on data science/ML with production deployments.
- Strong Python (≥3.9) engineering practices, testing, and code quality.
- Proficiency in ML libraries: scikit‑learn, XGBoost, LightGBM, TensorFlow, PyTorch.
- 3+ years of experience on Google Cloud (Vertex AI, BigQuery, Kafka).
- Deep knowledge of anomaly detection, time‑series forecasting, and optimization.
- Hands‑on with LLM integration (OpenAI, Google MCP, Hugging Face) and RAG.
**Key Responsibilities:**
- Design, build, and deploy scalable ML models for route optimization, ETA, fuel efficiency, capacity planning, and predictive maintenance.
- Develop anomaly detection and forecasting pipelines for trip deviations, theft, vehicle health, driver risk, and demand swings.
- Build low‑latency streaming ML pipelines, live feature engineering (Kafka, RisingWave), and batch/near‑real‑time workflows.
- Implement MLOps foundations: Vertex AI Pipelines, Feature Store, Model Registry; monitor, experiment (A/B), and detect drift.
- Construct and maintain analytical data models in BigQuery and AlloyDB PostgreSQL; optimize SQL for scale.
- Integrate LLM‑based systems (embeddings, vector search, RAG) for conversational analytics and knowledge discovery.
- Collaborate with data engineering, product, and platform teams to translate business problems into data‑science solutions.
- Mentor junior team members and promote best practices in model development and documentation.
**Required Skills:**
- Python, ML libraries (scikit‑learn, XGBoost, LightGBM, TensorFlow, PyTorch).
- Machine learning production lifecycle: training, deployment, monitoring, experimentation.
- Anomaly detection, time‑series forecasting, optimization, statistical modeling.
- Google Cloud services: Vertex AI, BigQuery, Kafka, RisingWave.
- LLM integration: embeddings, vector vectors, RAG.
- SQL, BigQuery performance tuning, feature engineering at scale.
**Required Education & Certifications:**
- Bachelor’s or Master’s degree in Computer Science, Data Science, Statistics, Engineering, or related field (degree equivalency acceptable).
- Relevant certifications (e.g., Google Cloud Professional Data Engineer, Machine Learning) are a plus.