Senior Data Engineer

Responsibilities

• Model Development:
  Design and implement advanced machine learning models for predictive maintenance, anomaly detection, and computer vision-based quality control.
• End-to-End Pipeline Construction:
  Architect data pipelines from ingestion (sensor data, PLC logs) to model deployment and monitoring using GCP and Python.
• Statistical Analysis:
  Apply rigorous statistical methods to identify patterns in manufacturing data that correlate with vehicle quality or equipment downtime.
• Cross-Functional Collaboration:
  
  Partner with Product and Engineering teams to translate manufacturing pain points into technical requirements and deliver user-centric data products.
• Technical Leadership:
  Act as a subject matter expert within ATP, conducting code reviews, mentoring junior scientists, and staying at the forefront of AI/ML research in the industrial space.
• Scalability:
  Ensure models are optimized for production environments, moving from localized pilots to global plant-wide deployments.
• Data Strategy:
  Work with data engineering to improve data collection protocols and sensor telemetry quality from the plant floor.

• Education:
  
  Requires a bachelor’s or foreign equivalent degree in computer science, information technology or a technology related field
• Master’s degree in Data Science, Computer Science, Statistics, Engineering, or a related quantitative field.
• Experience:
  
  5+ years of professional experience in a Data Science role, with a proven track record of deploying models into production environments.
• Technical Stack:
• Proficiency in Python (R and SQL are also highly valued).
• Expertise in machine learning frameworks:
  PyTorch, Tensor Flow, Scikit-learn, XGBoost, and LightGBM.
• Experience working within Google Cloud Platform (GCP) (Vertex AI, Big Query, Dataflow).
• Domain Knowledge:
  Previous experience with time-series analysis, industrial IoT data, or manufacturing quality systems.
• Preferred Requirements:
• Advanced Degree:
  PhD in a relevant field.
• Deep Learning:
  Experience with Computer Vision (CNNs) for automated inspection or Transformers for complex sequence modeling in sensor data.
• MLOps:
  Familiarity with CI/CD for machine learning, containerization (Docker/Kubernetes), and model monitoring tools.
• Communication:
  Ability to explain complex mathematical concepts to non-technical stakeholders (e.g., plant managers and design leads).
• Problem-Solving: A "product-first" mindset—focusing on the business impact of the model rather than just its accuracy metrics.