Job Title: Generative AI (GenAI) Engineer Experience Level: 7–12 Years Location: Remote About the Role • We are looking for a Generative AI Engineer with deep expertise in building solutions using LLMs, retrieval-augmented generation (RAG), agentic frameworks, and intelligent OCR pipelines. • The ideal candidate should have a strong foundation in Python, vector search, and Azure AI Services, and be hands-on with GenAI tooling like LangChain, LlamaIndex, and Semantic Kernel. • You will be instrumental in designing, developing, and deploying AI-powered solutions that combine language understanding, image processing, and autonomous agent capabilities to solve complex enterprise problems. Key Responsibilities • Design and implement end-to-end RAG pipelines using LangChain, LlamaIndex, or Semantic Kernel. • Integrate OCR tools (Tesseract, Azure Document Intelligence, John Snow Labs) into intelligent document processing workflows. • Build robust image preprocessing routines (denoising, contrast adjustment, binarization) to enhance OCR performance. • Develop agent-based architectures using CrewAI, MCP, or A2A frameworks with function calling and tool integrations. • Fine-tune prompts and build prompt-driven workflows for LLM performance optimization and hallucination control. • Create and manage embedding generation, vector databases, and semantic retrieval layers (e.g., FAISS, Azure AI Search). • Evaluate GenAI models using structured metrics, benchmarks, and A/B testing for continuous improvement. • Deploy scalable GenAI solutions using Azure OpenAI, AI Hub, Copilot Studio, and Azure ML Studio. • Collaborate cross-functionally with data scientists, MLOps, cloud engineers, and product teams to deliver AI-enabled products.