LLM Engineer

We are seeking a highly skilled LLM Engineer with deep expertise in chatbot implementations and large language models (LLMs) . The ideal candidate should have hands-on experience with Retrieval-Augmented Generation (RAG) , instruction fine-tuning , parameter-efficient fine-tuning (PEFT) techniques such as LoRA or QLoRA , and proficiency in frameworks like LangChain , LlamaIndex , Haystack , Rasa , or their equivalents. The role requires experience in designing and implementing at least two chatbot projects end-to-end, coupled with a strong understanding of requirement analysis, architecture planning , and solution strategy formulation . Bonus points for experience with Vision-Language Models (VLMs) and multimodal AI applications integrating text, image, video, and audio data. Key Responsibilities Design, architect, and develop intelligent chatbot systems using state-of-the-art LLM techniques. Analyze business and functional requirements and translate them into scalable LLM solutions. Implement Retrieval-Augmented Generation (RAG) pipelines using relevant libraries and vector databases. Apply instruction fine-tuning and PEFT techniques like LoRA/QLoRA for domain-specific customization. Build LLM applications using frameworks such as LangChain , LlamaIndex , Haystack , or Rasa . Integrate chatbots with enterprise systems, APIs, and document stores. Work with vector databases (e.g., Pinecone, FAISS, Weaviate, ChromaDB) and embedding models. Collaborate cross-functionally with design, product, and engineering teams for integration and deployment. (Preferred) Develop multimodal systems that process combinations of text, audio, video, and images. Stay up to date with the latest research in conversational AI, LLMs, and multimodal AI. Document technical architecture, processes, and best practices. Required Qualifications Bachelor's or Masters in Computer Science, Artificial Intelligence, Data Science, or equivalent. 6 to 9 years of total experience in software/AI development with minimum 2+ chatbot projects delivered using LLMs. Proficiency in RAG , instruction tuning , and parameter-efficient fine-tuning (LoRA/QLoRA) techniques. Strong expertise in one or more frameworks: LangChain , LlamaIndex , Haystack , Rasa , etc. Solid programming skills in Python and familiarity with Transformers , PyTorch , or TensorFlow . Experience with vector databases , embedding models , and NLP pipelines . Ability to understand business needs and independently drive solution strategy and implementation. Excellent communication and stakeholder engagement skills. Preferred Qualifications Exposure to multimodal AI and Vision-Language Models (VLMs) such as Flamingo, GPT-4V, or Kosmos. Experience with MLOps tools and deploying LLMs into scalable production environments. Understanding of prompt engineering, few-shot learning, and performance optimization for LLMs. Familiarity with model evaluation metrics specific to conversational and generative tasks. Soft Skills Strong analytical and problem-solving mindset. Self-motivated, with the ability to take initiative and ownership. Effective communicator with the ability to translate complex technical concepts into business outcomes. Comfortable working in agile, fast-paced environments.