Door categorieën bladeren
Ontdekken
Fiverr Pro
Nederlands
$
USD
Amulya L
@lakkuamulya
AI Engineer specializing in RAG, AI Agents and LLMs
India
Engels, Telugu
Over mij
I am an AI Engineer specializing in LLMs, RAG, AI agents, and Python. I help businesses and startups build custom AI chatbots, document Q&A systems, RAG pipelines, intelligent agents, and LLM-powered applications.
My expertise includes Python, LangChain, Hugging Face, vector databases, PostgreSQL, Docker, API integration, and prompt engineering.
I focus on reliable implementation, clear communication, and scalable solutions from prototype to production. Have an AI idea or automation requirement? Feel free to message me to discuss the best approach for your project.
Skills
Amulya L
offline •
Bekijk mijn diensten
AI chatbot development
I will build a custom rag ai chatbot with langchain, langgraph and your knowledge base
Portfolio
Werkervaring
AI Engineer 2
Amcodr IT Solutions • ZZP
Sep 2025 - Present • 10 mos
• Design and develop end-to-end Agentic AI systems using LangChain and LangGraph for autonomous multi-step reasoning, information retrieval, and complex task execution. • Build production-grade Retrieval-Augmented Generation (RAG) pipelines using FAISS, Pinecone, embeddings, semantic search, and LLM-based retrieval workflows. • Develop scalable Python and FastAPI backend services for AI-powered applications, including API integrations, conversation workflows, and stateful agent memory. • Implement multi-agent orchestration and intelligent workflow automation to coordinate specialized AI agents and execute complex tasks efficiently. • Engineer prompt templates, tool-calling workflows, and orchestration layers to improve response quality, reliability, and reduce hallucinations. • Design document ingestion, chunking, embedding, indexing, retrieval, and reranking pipelines for accurate knowledge-based question answering. • Work with LLMs and AI frameworks to build custom chatbots, AI assistants, document Q&A systems, and autonomous AI workflows. • Optimize retrieval quality, multi-turn reasoning, and application performance for real-world AI use cases. • Contribute across the complete AI development lifecycle, including solution architecture, prototyping, backend development, testing, optimization, and MVP delivery. Technologies: Python, LangChain, LangGraph, FastAPI, RAG, FAISS, Pinecone, LLMs, Prompt Engineering, Vector Search, REST APIs, and Agentic AI.
AI Engineer 1
PWC Solutions Limited • Fulltime
Jan 2024 - Aug 2025 • 1 yr 7 mos
• Developed an AI-powered enterprise assistant using GPT-4, LangChain, and Retrieval-Augmented Generation (RAG) to answer user queries related to flight pricing and operational knowledge. • Built end-to-end document ingestion, preprocessing, chunking, embedding, and semantic retrieval pipelines for accurate contextual question answering. • Implemented vector search and knowledge retrieval workflows using FAISS and ChromaDB with metadata-aware search to improve the relevance of retrieved information. • Designed and developed scalable FastAPI backend services for real-time AI query processing, API integration, and conversational workflows. • Implemented Redis caching and conversation memory to support efficient multi-turn interactions and improve application performance. • Worked on integrating Large Language Models with enterprise product documentation to create intelligent knowledge-based AI assistants. • Developed Retrieval-Augmented Generation workflows that combine semantic search with LLM-generated responses for accurate and context-aware answers. • Contributed to backend architecture, AI pipeline development, testing, optimization, and deployment of enterprise-grade AI applications. • Worked with AWS-based deployment environments and scalable backend components for production AI systems. Technologies: Python, GPT-4, LangChain, RAG, FastAPI, FAISS, ChromaDB, Redis, AWS, REST APIs, Vector Search, Semantic Search, and LLMs.
