Himanshu Negi

Architected an agentic, real-time offer orchestration engine where specialized agents (retrieval, pricing/optimization, and policy/guardrails) coordinate to personalise promotions across customer touchpoints using RAG with FAISS over Delta Lake and low-latency Databricks Model Serving. Collaborated with product managers and commercial stakeholders to shape the roadmap and evaluate emerging agent patterns for production.

Designed an agent-based data quality service that orchestrates schema detection, entity normalization, and validator/exception-handling agents to clean multi-retailer SKU feeds at scale. Wrapped model calls in PySpark UDFs for distributed inference, automated via Databricks Workflows and CI/CD.

Developed a multimodal, agentic extraction pipeline where vision, parsing, and compliance agents collaborate to derive brand, packaging, and volume from scanned images using Claude 3 Sonnet with Swin Transformer encoders. Orchestrated via Azure Event Hub with outputs persisted to Delta Lake.

Implemented a GS1 taxonomy classification service built around cooperating agents for inference, drift monitoring, and auto-retraining governance using Falcon 180B (LoRA-tuned) with a batch pipeline on Databricks.

Created a hybrid agent workflow where a retrieval agent surfaces candidate matches via embeddings and a reasoning/verification agent (Mixtral 8x7B) adjudicates receipt-to-SKU alignment, integrated into a streaming Databricks pipeline.

Built a multimodal attribute inference pipeline structured as cooperating vision-language, rules/consistency, and compliance agents to fill NutriScore, nutrition fields, and packaging types from names and images using LLaMA 3-8B with CLIP embeddings.

Developed a GenAI-powered orchestration system that ingests recipes from multiple websites, parses ingredients through structured extraction agents, and dynamically links them to real-time retailer offers via tagging, semantic reasoning, and business-rule agents.

Developed and deployed a Random Forest model on AWS SageMaker to calibrate IoT device temperatures in greenhouses, leveraging physics-based features and achieving a 20% improvement in prediction accuracy for real-time monitoring across 8000 devices.

Designed an AI-powered inventory system utilizing time series analysis to predict demand and automate replenishment processes, improving stock accuracy by 30%.

Developed an AI-driven quality control system using computer vision to detect manufacturing defects with 98% accuracy, reducing production errors by 35%.

Designed a content-based recommendation system for personalized banking product suggestions, increasing sales by 20% and improving customer satisfaction.

Developed an interactive chatbot using IBM Watson Assistant for financial product recommendations, improving customer engagement by 30%.

Built a predictive scorecard using logistic regression and lift charts to identify high-probability loan customers, boosting loan acquisition rates by 25%.

Forecasted monthly truck dealer sales using ARIMA and LSTM models with 95% accuracy to enhance dealership planning.

Predicted individual medical costs using Ridge, Lasso, and Elastic Net regression models, improving cost estimation accuracy by 15%.

Deployed AI-driven models for supply chain demand forecasting and inventory optimization, reducing operational costs by 25%.

Created an AI-powered customer support chatbot with GPT-based NLP for e-commerce, reducing response times by 40%.