Overview
This opportunity is with Big Entities , a leading software development and IT services company dedicated to delivering innovative software solutions that empower businesses to achieve exponential growth.
Job Description
Job Title : AI Engineer
Location : Onsite - Lahore
Experience : 2+ Years
Job Type : Full-Time
Job Summary : We are seeking an experienced AI / ML Engineer with a minimum of 2 years of hands-on experience in Natural Language Processing (NLP) and LLM (Large Language Model) -based solutions. The ideal candidate should have a strong background in Retrieval-Augmented Generation (RAG) , vector database design , chunking strategies , and chatbot development , along with proven expertise in fine-tuning and integrating LLMs for real-world applications.
Key Responsibilities
- Design and develop NLP pipelines to process and extract insights from unstructured data.
 - Build and optimize RAG (Retrieval-Augmented Generation) workflows for LLM-based systems.
 - Implement chunking strategies to improve information retrieval and response accuracy.
 - Work with vector databases (e.g., Pinecone, Weaviate, FAISS) to store and retrieve embeddings efficiently.
 - Develop conversational AI / chatbot solutions using modern frameworks and APIs.
 - Fine-tune, integrate, and deploy LLMs (Open-source or proprietary) based on application needs.
 - Collaborate with product and engineering teams to translate business requirements into intelligent AI-driven features.
 - Conduct experiments, evaluate model performance, and optimize pipelines for scalability and accuracy.
 
Required Skills & Qualifications
2+ years of experience in AI / ML Engineering , with a strong focus on NLP .Proven experience with RAG frameworks , LLM fine-tuning , and prompt engineering .Hands-on experience with vector databases such as FAISS, Pinecone, Chroma, Weaviate , etc.Strong understanding of embedding models , tokenization , and text chunking techniques .Experience in building chatbots and integrating with LLMs (OpenAI, Cohere, HuggingFace, etc.).Proficiency in Python and libraries like LangChain, Transformers, PyTorch, or TensorFlow .Experience with deploying models using APIs , microservices , or containerized solutions.Familiarity with MCP (Model Context Protocol), tool calling, and preferably agent-based frameworks (Agent Boot or similar) for building autonomous AI workflows.#J-18808-Ljbffr