I think rest of it is pretty much expected from the role. We would not be requiring them to form new models but they need to have exposure to Gen AI integration patterns. I have just updated the title in the JD
-------------------------------------------------------------------------------------------------------------------------------
We are looking for an enthusiastic Python AI Engineer to join our Controls Technology team and support the development and integration of generative AI solutions. In this hands-on role, you will work under the guidance of senior developers and AI architects to help build retrieval-grounded, context-aware, and increasingly agentic AI applications. You will contribute to reliable, AI-driven features while growing your expertise across the modern GenAI stack. This role focuses on applying pre-trained and hosted foundation models — through context engineering, RAG, knowledge graphs, and agentic workflows — rather than training or fine-tuning models.
This is a growth-oriented role: you'll take ownership of well-scoped components,



learn established patterns from senior engineers, and progressively increase your technical depth and independence.
Key Responsibilities
Assist in building and integrating generative AI applications using pre-trained and hosted foundation models (via managed GenAI APIs and open-model endpoints).
Support the implementation of context engineering workflows — assembling system instructions, retrieved knowledge, tool definitions, and conversation memory into reliable, token-effective prompts, following established patterns.
Contribute to prompt engineering (zero-shot, few-shot, chain-of-thought, role-based prompting) for AI-powered workflows.
Help develop and maintain Retrieval-Augmented Generation (RAG) components, including chunking, embedding, and semantic/keyword search.
Support the development of knowledge graph and Graph RAG pipelines under guidance to enable grounded, traceable responses.
Contribute to agentic

📌 Python AI Engineer (Pune)
🏢 Citi
📍 Pune