<p><p>We are looking for a Generative AI Expert with strong knowledge in Retrieval- Augmented Generation (RAG) and machine learning/deep learning (ML/DL).
You will work on building intelligent systems that combine large language models (LLMs) with document retrieval to generate accurate and context-aware responses.<br/><br/></p><p>Your role will involve developing and improving ML/DL models, fine-tuning LLMs, and integrating retrieval systems using vector databases.
Youll collaborate with cross- functional teams to build real-world AI solutions that make use of both unstructured data (like PDFs and web pages) and structured sources.</p><br/><p><b>Key Responsibilities :</b></p><p><p><b><br/></b></p>- Design, build, and optimize RAG pipelines for document-level and multi-turn QA systems.<br/><br/></p><p>- Fine-tune or prompt-tune foundation models (LLMs) for domain-specific tasks.<br/><br/></p><p>- Develop and deploy ML/DL models to support NLP/NLU tasks like summarization, classification, and retrieval scoring.<br/><br/></p><p>- Integrate vector databases, semantic search tools, and embedding models for high-performance document retrieval.<br/><br/></p><p>- Work with unstructured and semi-structured data sources (PDFs, HTML, JSON, SQL, etc.).<br/><br/></p><p>- Collaborate with data engineers, ML engineers, and product teams to build end- to-end generative AI solutions.<br/><br/></p><p>- Monitor performance, latency, and relevance metrics; iterate on retrieval and generation models.<br/><br/></p><p>- Implement prompt engineering strategies and hybrid approaches (rule-based + neural) to enhance model reliability.<br/><br/></p><p>- Contribute to research and innovation in applied generative AI, and stay up-to- date with the latest in LLM, RAG, and MLOps ecosystems.</p><br/><p><b>Key Skills Required :</b></p><p><p><b><br/></b></p>- Strong experience with RAG architectures and hybrid retrieval systems.<br/><br/></p><p>- Solid hands-on knowledge of LLMs (e.g., GPT, Mistral, LLaMA, Claude, DeepSeek, etc.) and embedding models (e.g., SBERT, OpenAI, HuggingFace models).<br/><br/></p><p>- Proficiency in machine learning / deep learning using PyTorch, TensorFlow, Hugging Face Transformers, etc.<br/><br/></p><p>- Experience with vector databases (e.g., FAISS, Weaviate, Pinecone, Qdrant).<br/><br/></p><p>- Experience in text chunking, retrieval scoring, prompt tuning, or LoRA/PEFT methods.<br/><br/></p><p>- Strong background in NLP, information retrieval, and knowledge graphs is a plus.<br/><br/></p><p>- Comfortable with Python and associated data science stacks (Pandas, NumPy, Scikit-learn).<br/><br/></p><p>- Experience working with real-world messy data (PDF parsing, OCR, HTML scraping, etc.)</p><br/></p> (ref:hirist.tech)