Lead Data Scientist

Role & responsibilities

• Design, build, and deploy machine learning models for predictive maintenance, process optimization, demand forecasting, and asset performance management.
• Work with large-scale datasets sourced from industrial systems to derive insights and inform strategic decisions.
• Develop and manage data pipelines for ingestion, transformation, and storage using tools such as Apache Spark, Airflow, or Kafka.
• Collaborate with domain experts to frame data science problems relevant to operations, manufacturing processes, logistics systems.
• Perform Exploratory data Analysis to understand data patterns and data readiness for Machine learning use cases.
• Deploy models in cloud or hybrid environments and monitor performance using MLOps best practices.
• Build and maintain visual dashboards and analytics reports using Power BI, Tableau, or Python-based frameworks.
• Communicate insights effectively to business and technical stakeholders.
• Apply generative AI and large language models (LLMs) to industrial data for document automation, decision support, and workflow optimization.

Technical Skills:

• Strong proficiency in Python and ML libraries (Scikit-learn, TensorFlow, PyTorch, XGBoost, etc.).
• Experience in Computer vison, Image processing, NLP and multi model techniques.
• Experience with data wrangling and processing large datasets using SQL, Pandas, Spark, or similar.
• Solid understanding of machine learning, time-series forecasting, statistical modelling, and MLOps practices.
• Experience with LLM fine-tuning, vector databases, or industrial NLP applications.
• Experience deploying models on cloud platforms (AWS, Azure, or GCP) using tools such as SageMaker, Vertex AI, or Databricks.
• Familiarity with data from industrial systems
• Hands-on with visualization tools (e.g., Power BI, Tableau).
• Certifications: Relevant certifications in Cloud-based Architecture (AWS, Azure, or GCP) are a plus.