Data Analyst (Analytics)

## About the Role

The Data Analyst (Analytics & Computer Vision) develops, automates, and maintains end-to-end data pipelines, relational database queries, BI dashboards, and computer vision models. This role involves extracting and wrangling unstructured/structured data from multiple sources, performing exploratory data analysis, designing executive KPI scorecards, and integrating OpenCV-based computer vision solutions for plant operations and quality monitoring.

## Key Responsibilities

• Develop, test, and maintain Python scripts using pandas and numpy to extract, parse, and clean unstructured and structured data from multi-source APIs, flat files, and databases.
• Identify, isolate, and clean missing values, duplicate records, outliers, and schema mismatches before ingestion into analytical stores.
• Automate scheduled ETL routines, batch scripts, and daily/weekly recurring reporting jobs to replace manual compilation workflows.
• Write, tune, and maintain complex SQL queries, views, stored procedures, and common table expressions (CTEs) across relational databases (PostgreSQL, MySQL, SQL Server) to retrieve datasets efficiently.
• Audit and optimize query runtimes to minimize database load during peak operational hours.
• Assist database administrators and data engineers in building clean, normalized reporting views.
• Design, publish, and maintain interactive business intelligence operational dashboards and KPI scorecards in tools like Power BI, Tableau, or Google Looker Studio.
• Build custom exploratory charts, distributions, and correlation matrices using matplotlib, seaborn, or plotly.
• Gather reporting requirements from departmental heads and translate them into intuitive visualization layouts.
• Perform deep-dive exploratory data analysis (EDA) to evaluate process bottlenecks, revenue variance, operational patterns, anomalies, and performance metrics across departments.
• Conduct cohort analyses, trend forecasting, and root-cause analyses to evaluate shifts in key business indicators.
• Prepare concise narrative summaries, executive slide decks, and quantitative reports for leadership.
• Perform regular reconciliations, data audits, and sanity checks against source transactional systems to maintain 100% data integrity and prevent reporting discrepancies.
• Maintain technical documentation for developed Python scripts, data dictionaries, metric definitions, query definitions, SOPs, and dashboard logic.
• Provide ad-hoc reporting support, field urgent data requests from operations, finance, and engineering teams, and conduct basic enablement sessions on dashboard usage.
• Develop, test, and deploy Computer Vision applications and image processing scripts using OpenCV for automated visual inspection, defect detection, and quality monitoring.
• Integrate computer vision model outputs into automated data pipelines and dashboard scorecards for operational monitoring.
• Implement IIoT 4.0 projects using sensor/Modbus/RS485/IEEE802.15.4/MQTT/CoAP/AMQP/LoRa WAN/zigbee protocols for communication, python/react/node.js as language and SQL/mySQL/PostgreSQL/InfluxDB/Prometheus

## Requirements

• Bachelor’s degree in computer science, Statistics, Mathematics, Information Technology, Engineering, or a related quantitative field. (Mandatory)
• 8–10+ years of hands-on experience in Data Wrangling, SQL Querying, BI Dashboarding, Pipeline Automation, and Computer Vision / OpenCV implementations.

## Preferred Qualifications

• Exposure to workflow scheduling tools (Cron, Apache Airflow).
• Basic familiarity with Git version control and collaborative repositories.
• Foundational knowledge of cloud data warehouses (AWS Redshift, BigQuery, or Snowflake).

## Competency Profile

• Strong statistical reasoning and pattern-detection capability.
• High attention to detail regarding data reconciliation, hygiene, and auditability.
• Effective communication skills to articulate analytical conclusions to cross-functional teams.

## Location & Work Mode

• Work from site/office (Ramgarh) Plant