Hire Ahamed K. - Generative AI Engineer

GenAI Engineer with 3 years of experience in designing and developing AI-powered solutions, intelligent chatbots, and Retrieval-Augmented Generation (RAG) applications. Skilled in Python, SQL, LangChain, OpenAI APIs, vector databases (Pinecone, Chroma, FAISS), and cloud platforms such as AWS. Experienced in building enterprise-grade document Q&A systems, AI automation tools, NLP pipelines, and LLM-powered workflows that improve operational efficiency and decision-making. Passionate about Generative AI, Machine Learning, and delivering scalable AI solutions that drive business value.

* LLM & RAG Development * Architected and deployed RAG pipelines using Pinecone and Chroma vector databases, enabling semantic document search across 10,000+ enterprise documents with >90% retrieval accuracy. * Designed and integrated LLM workflows using LangChain and GPT-4 for domain-specific enterprise Q&A, reducing average document lookup time by 60%. * Fine-tuned LLaMA 2 models using LoRA/QLoRA on internal knowledge bases, reducing hallucination rate by ~35% and improving factual accuracy for internal Q&A tasks. * Implemented LLM evaluation frameworks (RAGAS) and guardrail mechanisms to enforce output reliability and safety in production Q&A systems. * AI Automation & NLP * Engineered NLP pipelines for automated document extraction, entity recognition, classification, and summarization, processing 500+ business documents per day with 92% accuracy. * Automated extraction and classification of enterprise business documents using GPT-4 with custom prompt chains, eliminating 15+ hours of manual review weekly. * Built production-grade conversational AI chatbots with persistent memory, multi-turn context, and domain-specific reasoning using LangChain and FastAPI. * Infrastructure & Deployment * Built FastAPI inference services for LLM model serving, deployed on AWS EC2 with S3-backed document storage and Lambda-based event triggers. * Created PySpark-based ETL workflows on AWS, achieving a 40% improvement in pipeline performance and reducing data processing latency from 4 hours to under 2.5 hours. * Collaborated with engineering and cloud teams to design scalable AI architectures; documented best practices and conducted internal GenAI training sessions for 20+ team members.