About the role
We're seeking an Industrial AI Engineer to build and deploy production-grade AI/ML solutions that improve safety, reliability, product quality, and energy efficiency across petrochemical manufacturing operations. You will work closely with Process Engineers, Production, Process Technology, and Digital/IT teams to develop models and deliver them into real plant workflowsintegrated with historians, control systems, and decision-making processes.
This role combines AI and machine learning expertise with practical understanding of chemical processes and industrial data, including time-series signals, lab data, operating modes, and constraints in continuous manufacturing.
Key responsibilities
- Develop and deploy AI/ML solutions for manufacturing use cases such as:
- Process optimization (yield, energy, throughput, quality targets, constraint handling)
- Process anomaly detection and early warning systems for abnormal situations
- Soft sensors / virtual analyzers to estimate unmeasured quality variables
- Vision AI for safety, inspection, leakage/flare/smoke detection, and operational monitoring
- Agentic AI solutions (e.g., copilots for operators/engineers, workflow automation with guardrails)
- Translate plant problems into problem statements, define KPIs, and build measurable use cases
- Build end-to-end pipelines: data extraction, cleaning, feature engineering, model training, validation, deployment, monitoring, and retraining
- Work with plant data sources (e.g., PI historian, LIMS, MES, APC/PLC/DCS interfaces) and ensure data quality and contextualization (tags, units, equipment hierarchy)
- Implement MLOps practices (versioning, testing, CI/CD, model monitoring, drift detection, documentation)
Required qualifications
- Bachelor's or Master's degree in Chemical Engineering, Computer Science, Data Science, or related field
- Experience building ML models or industrial analytics solutions in manufacturing/energy/chemicals (preferred)
- Strong programming skills in Python (data wrangling, modeling, APIs) and Database (SQL), familiar with cloud platform Azure, AWS. Google Cloud
- Solid ML foundation: regression/classification, clustering, time-series methods, anomaly detection, model evaluation, and feature engineering
- Familiarity with process data and chemical manufacturing context (unit operations, process constraints, plant variability, operating modes, safety considerations)
- Experience with: REST APIs, git version control, CI/CD, Docker
- Self-driven and eager to continuously learn and stay current with emerging AI/ML technologies, able to upskill independently and proactively propose practical solutions
