Shape the future of enterprise solutions as a GenAI Architect. This role involves designing and leading the implementation of advanced Generative AI solutions across various business use cases. You will leverage deep expertise in LLMs, RAG, vector databases, and agentic AI frameworks, coupled with cloud-native deployment and CI/CD automation skills. Collaboration with stakeholders, data/ML teams, and engineering teams is key to delivering scalable, secure, and production-ready GenAI platforms and applications.

Architect and design comprehensive GenAI solutions, including RAG pipelines, agentic workflows, and multimodal use cases. Translate complex business challenges into actionable GenAI-driven use cases, solution blueprints, and strategic roadmaps. Develop and implement sophisticated retrieval systems using embeddings, chunking, metadata filtering, reranking, and evaluation metrics. Integrate and optimize vector databases for performance and relevance. Build robust agentic systems using frameworks like LangChain and LangGraph. Define secure and scalable cloud architecture patterns for GenAI deployments. Drive productionization through CI/CD pipelines and containerization best practices. Champion responsible AI practices covering security, governance, privacy, and compliance. Provide technical leadership, conduct reviews, and mentor engineering teams on best practices.

Proven experience in GenAI/LLM Architecture, including prompting, fine-tuning vs. RAG, embeddings, context windows, and hallucination control. Demonstrated success in designing enterprise GenAI use cases such as document Q&A, copilots, summarization, and knowledge assistants. Solid understanding of evaluation techniques, including groundedness, relevance, and cost trade-offs. Hands-on experience with vector databases and similarity search concepts, including tools like Pinecone, FAISS, Weaviate, Chroma, Milvus, or Azure AI Search. Strong knowledge of agentic AI frameworks including LangChain, LangGraph, and tool/function calling. Expertise in cloud architecture for GenAI workloads and CI/CD implementation for GenAI applications. Familiarity with DevOps/MLOps practices, containerization (Docker), orchestration (Kubernetes), and API deployment.