AI Services and chatbot for Grid Certification

Project Details

Project Overview

As a lead AI engineer at GridCert.ai, I architected and delivered automated certification workflows and customer-facing chatbots by leveraging custom-trained models and modern cloud services. My efforts transformed manual, error-prone processes into seamless, intelligent pipelines—dramatically reducing data-entry overhead and improving user satisfaction.

Core Contributions

Dataset Preparation & Model Training

• Document Analysis: Reviewed hundreds of PDF certification forms (solar and wind) to identify representative fields and structures.
• Custom Model Development: Trained multiple extraction models—each targeting a specific form variant—to accurately parse data (e.g., system specs, site details) and pre-populate the GridCert platform.
• Validation Workflows: Built LLM-powered validation services that cross-check extracted data against certification rules and customer inputs, flagging anomalies before submission.

Chatbot & Retrieval-Augmented Generation (RAG)

• Chatbot Design: Developed a customer support chatbot using Azure OpenAI and a vector database to store normative standards and certification guidelines.
• RAG Implementation: Implemented retrieval pipelines that fetch relevant regulatory text and feed it into the LLM, ensuring answers are grounded in up-to-date compliance documents.
• User Experience: Crafted conversational flows to guide users through common certification questions, dramatically reducing support tickets.

Messaging & Integration

• Kafka Messaging Queue: Integrated Apache Kafka to provide reliable, loss-resistant communication between Python microservices and the existing .NET GridCert.ai backend.
• Event-Driven Architecture: Designed topic schemas for "document-extracted," "validation-completed," and "submission-ready" events, enabling scalable, decoupled pipelines.

Documentation & Operations

• Technical Documentation: Authored end-user guides and investor-facing technical briefs, detailing model performance metrics, security safeguards, and compliance checkpoints.
• Cloud Services & DevOps: Orchestrated deployments using Docker, Terraform, and Helm on Azure; managed storage of raw and processed documents in Azure Blob Storage.
• CI/CD & Version Control: Maintained all code in GitHub repositories, with automated test suites and Azure Functions for serverless processing.

Technologies & Tools

• Languages & Frameworks: Python, C#, JavaScript, HTML/CSS
• AI & Data Services: Azure OpenAI, Azure Document Intelligence, Vector DB
• Cloud & DevOps: Azure Functions, Azure Blobs, Docker, Terraform, Helm
• Messaging & Integration: Apache Kafka, .NET backend
• Frontend & UX: WebSockets, Flutter (for prototype dashboards)
• Collaboration & Management: GitHub, Notion, Miro

Outcomes & Impact

• Efficiency Gains: Automated data extraction reduced manual form-filling workload by over 80%, accelerating certification throughput.
• Accuracy Improvements: Validation services cut error rates in customer submissions by 60%, minimizing rework and audit flags.
• Scalable Customer Support: The chatbot handled 70% of common inquiries autonomously, freeing up support staff for high-value tasks.