Position Title

Senior Data Scientist

Purpose of the Position (Job Summary)

This role is ideal for someone with a strong product mindset and a proven ability to work independently, while mentoring a small team.

On site role at Jhagadia, Bharuch. 

 

Key Individual Accountabilities

Data Science Solution Development

· Design and develop predictive and prescriptive models for manufacturing challenges such as process optimization, yield prediction, quality forecasting, downtime prevention, and energy usage minimization.

· Perform robust exploratory data analysis (EDA) and apply advanced statistical and machine learning techniques (supervised and unsupervised).

· Translate physical and chemical process knowledge into mathematical features or constraints in models.

· Deploy models into production environments (on-prem or cloud) with high robustness and monitoring.

Team Leadership & Management

· Lead a compact data science pod (2-3 members), assigning responsibilities, reviewing work, and mentoring junior data scientists or interns.

· Own the entire data science lifecycle: problem framing, model development, validation, deployment, monitoring, and retraining protocols.

Stakeholder Engagement & Collaboration

· Work directly with Process Engineers, Plant Operators, DCS system owners, and Business Heads to identify pain points and convert them into use-cases.

· Collaborate with Data Engineers and IT to ensure data pipelines and model interfaces are robust, secure, and scalable.

· Act as a translator between manufacturing business units and technical teams to ensure alignment and impact.

Solution Ownership & Documentation

· Independently manage and maintain use-cases through versioned model management, robust documentation, and logging.

· Define and monitor model KPIs (e.g., drift, accuracy, business impact) post-deployment and lead remediation efforts.

Key Interactions

Internal

HODs Unit Management  Team Members 

Externals 

Vendors Technical & Behavioral Skills & Knowledge

· 8+ years of experience in Data Science roles, with a strong portfolio of deployed use-cases in manufacturing, energy, or process industries.

· Proven track record of end-to-end model delivery (from data prep to business value realization).

· Master’s or PhD in Data Science, Computer Science Engineering, Applied Mathematics, Chemical Engineering, Mechanical Engineering, or a related quantitative discipline.

· Expertise in Python (Pandas, Scikit-learn, Pyomo, XGBoost, etc.), and experience with cloud ML tooling (Azure ML, AWS Sagemaker, etc.).

· Familiarity with plant control systems (DCS, SCADA, OPC UA), historian databases (PI, Aspen IP.21), and time-series data.

· Experience in developing optimization models (LP, MILP, MINLP) for process or resource allocation problems is a strong plus.

 

Key Performance Indicators

· Familiarity with GenAI/RAG frameworks for use-cases like documentation assistants or control room chatbots.

· Exposure to process simulation tools (Aspen Plus/HYSYS), sensor data fusion, or physics-informed ML.

· Experience working in Agile product development environments.

· Hands-on experience building dashboards (PowerBI, Streamlit) for model visualization and interaction.

· Self-starter who thrives in low-data-maturity environments.

· Excellent problem-solving and analytical thinking tailored to real-world industrial constraints.

· Strong communication skills to explain complex technical outcomes to non-technical stakeholders.

· Ability to balance short-term delivery with long-term platform and model sustainability.

Competencies Agile Towards Change and Innovation, PL1Builds a Performance & Development Culture , PL1Builds Partnership with Stakeholders, PL1Executes Efficiently , PL1Focused on Achieving Results, PL1Thinks Strategically and Acts Decisively, PL1