Assisted professors in teaching undergraduate level course in separation processes, including distillation, filtration, centrifugation, and chromatography.• Graded assignments, exams, and provided constructive feedback to students to help them improve their understanding of the material.• Maintained a positive and engaging learning environment by facilitating group discussions and encouraging student participation.• Demonstrated strong interpersonal and communication skills, working effectively with a diverse group of students, faculty and staff.• Demonstrated a deep understanding of separation processes and a passion for education and helping students succeed.

• Identified process improvement opportunity in process efficiency with a data-driven survey and feedback from Indian Ministry of Environment and opportunities to reduce waste production with an increase in profit.• Built an automated ETL pipeline to extract experimental data, transformed and loaded it into Amazon RedShift, for SME (Subject Matter Experts) engagement. • Queried, cleaned, and engineered features from the data, creating new variables like normalised adsorption rates, and prepared the dataset for modelling.• Applied optimisation methods (linear programming) and machine learning (support vector machines) in Python to refine the batch-to-continuous transformation of the activated carbon pilot plant, achieving a 5% production boost & 0.07-fold improvement in process efficiency.• Utilised agile methodologies, including Scrum board for iterative development of the machine learning model and engagement dashboard for SMEs.• Collaborated with SMEs to design an automated Tableau Dashboard that captured key metrics, offering real-time and leading to a ₹36,000 profit increase for the plant.• Served as liaison between the Research committee and the production team to streamline the feedback implementation resulting in achieving set deadlines almost 3 days before submission.

• Used Python libraries like Pandas and SciPy to manipulate and analyse a dataset of 500,000+ rows, covering production metrics such as material flow, machine uptime, and process delays.• Applied machine learning algorithms, including random forests and logistic regression from scikit-learn, to identify inefficiencies in the production process.• Implemented discrete event simulation using SimPy to model and test production configurations, optimising workflows and reducing bottlenecks.• Achieved a 4.36% efficiency improvement in the Chocolate and Dairy divisions through data-driven simulations and workflow optimisation. • Collaborated with production and engineering teams to develop, test, and deploy analytics solutions, such as and pricing models, to enhance operational efficiency by 3.6% and profit by ₹2000 per 200 items.

• Utilised Hadoop and Spark to inspect and track color/pigment ratios, batch process times, GST invoices, and weight calculations from earlier batches.• Initiated process automation using Power BI and Tableau, leading to an 8% reduction in defective return materials.