Job Summary:

We are seeking an experienced AI/ML Engineer with a minimum of 4 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:

• 3+ 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.

Nice to Have:

• Experience with multi-modal models (e.g., text and images).
• Knowledge of data privacy and security best practices in AI systems.
• Exposure to cloud services, especially Azure, for AI/ML workloads.

This is a full-time position in DHA Phase 3 Lahore.