Sr Advanced Software Engr

.

Job Title: Senior Process Engineer – Data Analytics and Machine Learning - 155970

Experience: 8–12 years

About the Role

We are seeking a strong Senior Process Engineer with deep refinery/petrochemical plant experience, supported by strong skills in data analysis, Python, and machine learning. The ideal candidate will understand plant operations, process behavior, control systems, and safety practices, and will be able to apply analytical and ML techniques to improve process performance, reliability, decision-making, and operational efficiency.

• Strong refinery/petrochemical process engineering background, including hands-on understanding of P&IDs, PFDs, unit operations, process equipment, and plant operating constraints.
• In-depth knowledge of plant operations, standard operating procedures, safety practices, start-up and shutdown activities, process control, PLC/DCS automation systems, interlocks, control narratives, and operating parameters.

Key Responsibilities

• Analyze refinery/petrochemical process data to identify performance gaps, operating trends, process deviations, and improvement opportunities.
• Work with structured and unstructured plant data, including historian, laboratory, operations, and equipment-related datasets.
• Identify patterns, correlations, anomalies, and early indicators from large volumes of operational and process data.
• Apply statistical, data analysis, and machine learning techniques to solve practical process engineering and operational problems.
• Use Python to clean, transform, analyze, and visualize process data, and to support proof-of-concept development for analytics and ML use cases.
• Translate process engineering knowledge into clear analytical requirements, features, rules, and validation criteria for data science and software teams.
• Collaborate with operations, process engineering, data science, and software teams to convert plant problems into deployable analytics and ML solutions.
• Support the development and enhancement of analytics and machine learning platforms by providing process-domain expertise, model validation inputs, and practical deployment guidance.

Required Qualifications and Skills

• 8–12 years of process engineering experience in refinery/petrochemical or closely related process-industry environments.
• Strong knowledge of refinery/petrochemical process units, plant operations, process control, safety systems, and real-time operating data.
• Good hands-on Python skills for data analysis, automation, visualization, and prototype development; production software engineering experience is a plus.
• Experience using data analysis libraries such as Pandas and NumPy to work with engineering and operational datasets.
• Working knowledge of statistical analysis, trend analysis, anomaly detection, and feature engineering for process data.
• Exposure to machine learning concepts and practical ML use cases such as soft sensors, predictive monitoring, fault detection, optimization, or reliability analytics.
• Ability to validate analytical and ML outputs using sound process engineering judgment and plant operating context.
• Proficiency in SQL and experience extracting, joining, and interpreting plant, laboratory, historian, or equipment datasets.
• Ability to communicate insights clearly to process engineers, operations stakeholders, data scientists, and software teams.
• Experience with PySpark, scalable data processing, CI/CD, DevOps, or production deployment practices is desirable but not mandatory.
• Hands-on experience applying machine learning or advanced analytics to refinery/petrochemical process-industry problems such as yield improvement, energy optimization, constraint monitoring, abnormal situation detection, or predictive maintenance.
• Experience working with plant historians, DCS/PLC data, laboratory information systems, maintenance systems, or other industrial data sources.
• Ability to bridge process engineering, operations, data science, and software teams to ensure analytics solutions are technically sound, operationally practical, and business-relevant.