We’re building an Industrial Digital Twin & Generative AI platform that connects real-world operations with intelligent conversational systems. We’re looking for an experienced AI Engineer to design and deploy RAG/CAG-driven AI architectures and AWS-based chatbots that enhance decision-making and automation in industrial environments. You’ll collaborate with our core team to architect scalable, secure, and adaptive LLM workflows using LangChain, LlamaIndex, and AWS SageMaker/Bedrock. This role involves both innovation and implementation — perfect for someone who wants to push Generative AI beyond prototypes. Deliverables : • Develop and maintain RAG pipelines using vector databases and document retrieval frameworks to enable data-grounded LLM responses. • Implement CAG frameworks that enhance contextual reasoning and ensure domain-accurate response generation. • Deploy and optimize conversational AI systems (internal & customer-facing chatbots) on AWS — leveraging SageMaker, ECS, Lambda, Bedrock, and API Gateway. • Integrate AI services seamlessly with existing backend systems and APIs for real-world interoperability. • Ensure scalability, observability, and cost efficiency across deployed AI workloads through best practices in MLOps and monitoring. • Collaborate with data and product teams to define model evaluation metrics, continuous improvement loops, and system feedback pipelines.