Projects
Some of Harsha's interesting projects are:
| Topic | Company | Description | Topics |
|---|---|---|---|
| Predicting aircraft engine failure | Global Aircraft Engine Manufacturer | Explored unsupervised learning methods to predict aircraft engine part failures and deployed physics-informed ML predictive maintenance models for two parts across 1,000+ engines. | Predictive Maintenance, Machine Learning, Unsupervised Learning, Aerospace |
| Quiz Generation | Pharma Company | Led the end-to-end design and delivery of a Generative AI product to test sales agents knowledge about the drugs, integrating quiz generation, Q&A chatbot, and performance dashboards using AWS, FastAPI, React, and LangChain. | Generative AI, RAG, Product Delivery, AWS |
| Supply Chain Optimisation | Walmart | Improved under-stocking for Walmart’s LATAM supply chain, delivering $1.2M/month in savings by modelling supplier delivery risk, forecasting lead times, and suggesting an optimised EOQ/reorder points that integrate these risks via integer programming and Monte Carlo simulations | Supply Chain Analytics, Predictive Analytics, Prescriptive Analytics, Optimisation |
| AI-Powered Predictive Maintenance Strategy Optimisation Platform | Manufacturing AI Accelerator | Designed an AI-powered platform combining Generative AI, machine learning, reliability engineering, and agentic planning to clean SAP maintenance data, identify failure and replacement events, analyse asset reliability, and recommend risk-based maintenance schedules. | Generative AI, Agentic AI, Predictive Maintenance, Reliability Engineering, Optimisation, SAP |
| Automating Bid Generation | Pharma Manufacturer | Developed a GenAI-based tool to automate the extraction of key data from US Government pre-solicitation and solicitation bids, accelerating bid creation for sales and supply chain teams | Generative AI |
| Demand Forecasting | Large FMCG Manufacturer | Built and deployed granular volume forecasting models across the North American market using Python, PySpark, and Databricks, achieving 90% accuracy and improving planning across customer, location, and package dimensions | Demand Forecasting, Machine Learning, MLOps, Azure, PySpark |
| Intelligent annotation | Global aircraft engine Manufacturer | Created a “Human with AI” tool that saved 1,200+ man-hours by assisting SMEs in diagnosing engine issues for a major manufacturing company | Predictive Maintenance, Human-in-the-Loop AI, Aerospace, Machine Learning |
| Workforce Management | Global FMCG manufacturer | Developed a proof of concept (PoC) application that assigned jobs in a manufacturing plant based on contractor preferences, past performance and availability | Workforce Optimisation, Operations Research, Optimisation |
| Compititive intelligence | Pharma Manufacturer | Developed a competitive intelligence pipeline for a pharma manufacturer leveraging FDA inspection news via Google News API and web scraping, integrated with PaLM 2 for analysis, and deployed using Airflow, Vertex AI, and BigQuery on Google Cloud Platform | Generative AI, Competitive Intelligence, Google Cloud, Vertex AI |
| Supplier Selection | Large manufacturer | Developed a supplier optimisation engine that influenced £180M in sourcing decisions | Supplier Optimisation, Procurement, Operations Research |
| Data Center of excellence | Agriculturer Global Capability Center | Set up a Data Centre of Excellence using Azure Cloud and built scalable data pipelines for a global GCC | Data Engineering, Azure, Data Strategy |
| Identification of ingredients | ClarusOne | Built an NLP-based PoC to estimate ingredient composition and cost in food items using USDA nutrient data, aiding sourcing managers and food scientists in procurement decisions | Natural Language Processing, Cost Intelligence, Procurement |
| Creating Rewards and Returns Contests | Tata AIA Life Insurance Company | Created "Rewards and Returns" contests for an insurance client to motivate agents to perform better and increase efficiency | Predictive Analytics, Clustering, Optimisation |
| Agentic AI for Source-of-Wealth Validation | Banking AI Accelerator | Developed an agentic AI accelerator to automate KYC (Know your customer), SOW (Statement of wealth), policy compliance checks, evidence verification, gap analysis, and narrative generation for source-of-wealth validation. | Agentic AI, Generative AI, Risk Analytics, Financial Services |