Senior Data Scientist - Operation Analyst

Tiger Analytics is looking for experienced Data Scientists to join our fast-growing advanced analytics consulting firm. Our consultants bring deep expertise in Data Science, Machine Learning and AI. We are the trusted analytics partner for multiple Fortune 500 companies, enabling them to generate business value from data. Our business value and leadership has been recognized by various market research firms, including Forrester and Gartner. We are looking for top-notch talent as we continue to build the best global analytics consulting team in the world.

We are seeking an experienced Senior Data Scientist to drive advanced analytics initiatives focused on improving operations Analytics accuracy. This role requires a strong blend of machine learning expertise, deep learning knowledge, and hands-on healthcare domain understanding.

Key Responsibilities

• Getting EMPRV (Electronic Data Systems Maintenance Process Reengineering Vision) data into the lakehouse. This means extracting decades of work orders, asset hierarchy, maintenance history, and materials data (probably from an Oracle database) into Delta tables.
• Maintenance and work-order analytics. Examples include backlog and aging, planned versus actual labor and cost, repeat work orders on the same asset, crew productivity, and schedule adherence etc.
• Reliability and asset-health modeling. This covers failure patterns, time-to-failure and survival models, risk-based prioritization of maintenance, and anomaly detection on cost or frequency.
• Materials and inventory analytics. Examples are demand forecasting for spares, slow-moving or obsolete stock, and bill-of-materials consumption patterns.
• A Databricks App as the front end. This would replace legacy EMPRV queries and reports with a self-service tool for ops users
• Text analytics on work-order notes. Technician free-text comments are usually the richest and messiest part of EAM data. Classifying failure modes or cause codes from that text, including with LLMs

Requirements

Core (must-have)

• Python and PySpark programming experience. Strong SQL
• The Databricks platform. That includes Delta Lake, Unity Catalog, Workflows/Jobs, SQL warehouses, and ideally Delta Live Tables or Lakeflow. Basic familiarity with AWS (S3, IAM) will help
• Databricks Apps. The candidate should be able to build an app in Streamlit, Dash, or Gradio, connect it to SQL warehouses or Unity Catalog tables, and handle service principals, permissions, and deployment

Analytical (should-have)

• Statistical and ML modeling (preferably for operations). Relevant methods include classification and regression, time-series forecasting, survival and reliability analysis, and anomaly detection.
• NLP or LLM experience on unstructured text
• MLflow for experiment tracking and model deployment.

Soft skills

• Comfort working directly with operations stakeholders. The candidate will be translating tribal knowledge about how EMPRV is actually used into data definitions, with limited documentation to lean on.

Benefits

This position offers an excellent opportunity for significant career development in a fast-growing and challenging entrepreneurial environment with a high degree of individual responsibility.