Dr. Joyjit Chatterjee

Leading AI/ML solutions for Fortune 500 & FTSE 250 clients across FMCG, agriculture, aviation, and healthcare. Mentoring data scientists and senior data scientists across the EPAM data practice.

Notable Achievements:

• Leading the development of AI/ML solutions as part of the UK & Western Europe AI/ML Consulting team, curating and collaborating on multi-million £ data science projects across Europe and North America.
• Mentoring data scientists and senior data scientists across the EPAM data practice.
• Conducted several Technical as well as Project Interviews – hiring and assembling multiple business analysts, data scientists, data engineers for EPAM clients' projects.
• Authored articles for EPAM's Supply Chain Management (SCM) community, co-organised educational workshops on AI for EPAM's clients, reviewed editorial content for GenAI-X community.
• Delivering end-to-end AI/ML and GenAI solutions using LLMs, RAG, Agentic AI (LangChain, PhiData, CrewAI), Azure OpenAI Service, Python, Retool, Postman, pgAdmin, APIs.

Drove data & AI-first approach for continuous improvement across manufacturing stages and QC processes, enhancing Overall Equipment Effectiveness (OEE) in factories.

• Created a holistic manufacturing data model for CPV, identifying key factors driving waste and quality deviations across multiple product lines
• Demonstrated potential savings of £300k/year through predictive analytics for waste reduction in factories
• Achieved 30% waste reduction demonstrated through AI-driven process optimisation models
• Developed a data-driven tool for Cost-to-Serve (CTS) optimisation in logistics, identifying opportunities to consolidate shipments and convert Less than Truck Load (LTL) to Full Truck Load (FTL)
• Leveraged Generative AI (via open-source LLMs in Ollama & LangChain) to enhance accessibility to complex AI analytical insights in manufacturing by summarizing them into simplified, SME-accessible formats
• Built Agile capacity prediction models for sprint planning and resource allocation
• Represented Reckitt at external industry forums and conferences, sharing best practices in AI for manufacturing
• Collaborated with cross-functional teams across R&D, Quality, and Manufacturing Engineering
• Drove stakeholder engagement with senior leadership to align AI initiatives with business strategy

Led the AI workstream of a $200k Innovate UK Knowledge Transfer Partnership (KTP) project between Reckitt and the University of Hull. Developed hybrid AI models combining laboratory data with chemistry domain knowledge for pharmaceutical and nutraceutical product development.

• Received Innovate UK Certificate of Excellence - Outstanding grade (highest possible) for the KTP project outcomes
• Delivered a $200k KTP project developing AI solutions for R&D New Product Development (NPD) and Existing Product Development (EPD)
• Demonstrated potential savings of $780k through AI-driven stability and shelf-life predictions
• Saved 10,000+ lab hours through automated AI-based shelf-life prediction models
• Developed a shelf-life prediction app enabling scientists to predict product stability without running lengthy real-time experiments
• Reduced energy consumption demonstrating 2k+ kWh/year potential savings through optimised experimental design
• Built hybrid AI models combining laboratory data (LIMS) with domain-specific chemistry knowledge (e.g. SMILES molecular fingerprints) for formulation development
• Published research findings in top-tier venues (Cambridge University Press, Cell Press/Patterns)
• Highlighted as an Ashorne Hill KTP success story
• Contributed to transforming Reckitt's AI landscape in R&D applications

Pursued R&D in hybrid AI models combining laboratory data with chemistry domain-specific knowledge for pharmaceutical and nutraceutical product development. Collaborated with Reckitt on R&D NPD & EPD applications.

• Conducted post-doctoral research as academic partner on the Innovate UK KTP project
• Mentored PhD students and delivered guest lectures in AI/ML
• Published collaborative research in high-impact journals
• Participated in recruitment panels for postdoctoral researchers and research associates

Visiting research stay at the University of Bremen as part of the Green Talents Award from the German Federal Ministry of Education and Research (BMBF). Collaborated on sustainable AI and energy research.

• Worked in project EisAuge for applying AI to detect icing in wind turbine blades, developing deep learning techniques leveraging transfer learning for generalised ice detection
• Research resulted in a novel generalised ice detection system that can predict ice across multiple wind farms, when AI models are trained with data from only a single/distinct wind farm
• Pursued research virtually (June-July 2022) and in-person (July-August 2022) based on the Green Talents Award from the German Federal Ministry of Education & Research

Conducted doctoral research on "Explainable AI for Operations & Maintenance of Wind Turbines" under the supervision of Dr. Nina Dethlefs. Developed novel AI techniques for fault detection, diagnosis, and prognosis using SCADA data.

• Developed deep learning models with knowledge transfer for explainable anomaly prediction in wind turbines using SCADA data
• Pioneered the use of knowledge graphs for wind turbine O&M, linking SCADA signals, faults, and maintenance actions
• Built a natural language generation (NLG) system to convert complex SCADA data patterns into human-readable maintenance reports
• Created an automated question-answering system for interactive decision support in wind turbine O&M
• Applied explainable AI (XAI) techniques including Natural Language Generation, Temporal Causal Inference, and Knowledge Graphs for transparent and explainable anomaly prediction
• Developed causal inference methods for temporal analysis of SCADA time-series data
• Published 7+ papers including in Wind Energy (Wiley), IEEE Access, Renewable & Sustainable Energy Reviews (Elsevier)
• Presented at major conferences including NeurIPS, KDD, ECAI, IJCNN, WindEurope
• Won Young Researcher Award from IEEE UK & Ireland (2019)
• Completed a scientometric review of AI for wind turbine O&M, which became a top-cited paper

Technology internship as part of Internship Experience UK programme. Focused on Agile Software Development, Communications, Product Development Planning and Testing & Deployment for incorporating Facial Verification technology into existing banking apps.

Research internship funded by the Ministry of Education, Taiwan as part of TEEP@India program. Designed a software application for recognizing emotions in human speech signals using data analytics, machine learning and signal processing.

Selected among 30 students from across India for the Mentor Higher Education Program on Verification of Electronic Design and Systems using System Verilog. Designed projects including Universal Asynchronous Receiver Transmitter, RISC Microprocessors, and FIFO buffer.