Partha Pratim Nandi
About
Detail
AI Software Developer at Fraunhofer IIS
Erlangen, Bavaria, Germany
Résumé
Jobs
verified_user
0% verified
- FAI Software DeveloperFraunhofer IISSep 2022 - Jun 2023 (10 months)• Built a custom AI chatbot for an e-commerce client using GPT-4 and LangChain with RAG, reducing customer support ticket volume by 45% and improving response accuracy to 92%. • Designed and deployed an intelligent document processing system using LlamaIndex, Pinecone, and FastAPI for a FinTech startup, enabling semantic search across 100K+ financial documents. • Developed multi-agent AI workflows using CrewAI and LangGraph for a marketing agency, automating lead research, content generation, and outreach — saving 20+ hours/week of manual work. • Created AI-powered automation pipelines using n8n, Make, and Zapier integrated with CRMs (GoHighLevel, HubSpot), reducing manual data entry by 80% for a real estate firm. • Delivered prompt enginee
- AAI Engineer & ConsultantAum SolutionsJan 2020 - Dec 2021 (2 years)• Designed and built production-grade AI chatbots and virtual assistants using LLMs (GPT-4, Claude, Gemini), reducing internal support response time by 60% across research teams. • Architected RAG pipelines using LangChain, LlamaIndex, and vector databases (Pinecone, ChromaDB, FAISS) for intelligent document retrieval and semantic search across 50K+ research documents. • Developed multi-agent AI systems and agentic workflows using CrewAI and LangGraph, automating complex multi-step research and data processing tasks. • Built and maintained scalable REST APIs with Python and FastAPI, serving AI models in production environments on AWS and Azure. • Implemented end-to-end AI automation pipelines using n8n, Make, and Airflow, integrating AI ser
Education
verified_user
0% verified
- FMaster of Science (M.S.) – Data ScienceFAU Erlangen-Nürnberg, GermanyOct 2022 - Feb 2026 (3 years 5 months)Relevant Coursework: Data Management, Data Engineering, Machine Learning, Statistical Analysis
- GBachelor of Engineering (B.E.) – Computer EngineeringGujarat Technological University (GTU), IndiaJul 2016 - Sep 2020 (4 years 3 months)Relevant Coursework: Software Engineering, Database Management Systems, Data Structures, Algorithms
Projects (professional or personal)
verified_user
0% verified
- SAI-Powered Content Generation PlatformSaasJan 2026 - Jun 2026 (6 months)• Architected a scalable multi-model SaaS content platform that intelligently routes generation requests to GPT-4, Claude, or Gemini based on content type, quality requirements, and cost optimization. • Developed a custom prompt engineering framework with a dynamic template system supporting 20+ content formats (blogs, emails, ads, social posts, product descriptions), integrated with a Pinecone-powered RAG pipeline for brand voice consistency. • Platform handles 10,000+ daily API requests with 99.9% uptime, increased client content output by 10x, and reduced content production costs by 70%. Deployed on AWS with Docker, FastAPI, and Redis.
Intelligent Document Q&A System with RAGFintechJan 2025 - Dec 2025 (1 year)• Designed and deployed a semantic search and document intelligence system for a FinTech startup, enabling instant natural-language Q&A across 100K+ financial documents including regulatory filings, contracts, and compliance reports. • Built the RAG pipeline using LlamaIndex for document ingestion and chunking, Pinecone as the vector store, and FastAPI for the serving layer, achieving 95%+ retrieval accuracy with sub-2-second response times. • Implemented hybrid search combining dense embeddings with keyword-based BM25 retrieval, along with metadata filtering for document type, date range, and compliance category.- MMulti-Agent AI Workflow for Lead GenerationMarketing AgencyJan 2024 - Dec 2024 (1 year)• Developed an autonomous multi-agent system using CrewAI and LangGraph that orchestrates specialized AI agents for lead research, qualification scoring, and personalized outreach email generation. • Agents autonomously scrape prospect data, enrich profiles via third-party APIs, score leads using custom criteria, and generate tailored outreach sequences — all without human intervention. • Saved 20+ hours/week of manual prospecting work and increased qualified lead pipeline by 3x, while reducing cost-per-lead by 60% for the agency’s clients.
- AI Automation Pipeline for Real Estate CRMGoHighLevelJan 2020 - Dec 2020 (1 year)• Deployed a fully automated AI pipeline integrating GoHighLevel CRM with n8n, Make (Integromat), and Zapier to orchestrate lead capture, scoring, routing, and multi-channel follow-up sequences across email and SMS. • Built custom Python scripts with FastAPI for intelligent lead scoring logic, CRM data enrichment via webhooks, and real-time lead capture from Facebook Ads, Google Ads, and landing pages. • Reduced manual data entry by 80% (freeing 15+ hours/week for the sales team) and increased lead conversion rates by 35% through automated, behavior-triggered follow-up workflows.
- EAI-Powered Customer Support ChatbotE-commerceJan 2019 - Dec 2019 (1 year)• Engineered a production-grade conversational AI chatbot using GPT-4 and LangChain with a Retrieval-Augmented Generation (RAG) pipeline, enabling context-aware responses grounded in the client’s product catalog and support knowledge base. • Integrated the chatbot with Shopify storefront, Zendesk ticketing system, and a custom vector-indexed FAQ database using Pinecone for real-time semantic retrieval. • Reduced customer support ticket volume by 45% within the first month and improved response accuracy to 92%, handling 2,000+ daily customer interactions autonomously.