AI Engineer (Gen AI)

Brief DescriptionExperience: 6+ Years Location: Technopark Trivandrum 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. Your role will involve developing and improving ML/DL models, fine-tuning LLMs, and integrating retrieval systems using vector databases. You’ll 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.  Key Responsibilities:  • Design, build, and optimize RAG pipelines for document-level and multi-turn QA systems. • Fine-tune or prompt-tune foundation models (LLMs) for domain-specific tasks. • Develop and deploy ML/DL models to support NLP/NLU tasks like summarization, classification, and retrieval scoring. • Integrate vector databases, semantic search tools, and embedding models for high-performance document retrieval. • Work with unstructured and semi-structured data sources (PDFs, HTML, JSON, SQL, etc.). • Collaborate with data engineers, ML engineers, and product teams to build end to-end generative AI solutions. • Monitor performance, latency, and relevance metrics; iterate on retrieval and generation models. • Implement prompt engineering strategies and hybrid approaches (rule-based + neural) to enhance model reliability. • Contribute to research and innovation in applied generative AI, and stay up-to date with the latest in LLM, RAG, and MLOps ecosystems.Preferred Skills• Strong experience with RAG architectures and hybrid retrieval systems. • Solid hands-on knowledge of LLMs (e.g., GPT, Mistral, LLaMA, Claude, DeepSeek, etc.) and embedding models (e.g., SBERT, OpenAI, HuggingFace models). • Proficiency in machine learning / deep learning using PyTorch, TensorFlow, Hugging Face Transformers, etc. • Experience with vector databases (e.g., FAISS, Weaviate, Pinecone, Qdrant). • Experience in text chunking, retrieval scoring, prompt tuning, or LoRA/PEFT methods. • Strong background in NLP, information retrieval, and knowledge graphs is a plus. • Comfortable with Python and associated data science stacks (Pandas, NumPy, Scikit-learn). • Experience working with real-world messy data (PDF parsing, OCR, HTML scraping, etc.)