Job Overview
We are seeking an experienced Senior Generative AI Developer to help drive the design, development, and integration of state-of-the-art Generative AI and agentic AI solutions across our enterprise Controls Technology platform. You will collaborate with cross-functional teams, contribute deep technical expertise in context engineering, retrieval systems, knowledge graphs, and multi-agent orchestration, and play a key role in delivering scalable, grounded AI solutions to enhance automation and operational efficiency. This role centers on architecting robust applications and agent systems on top of pre-trained and hosted foundation models — not on training or fine-tuning models.
Key Responsibilities
Collaborate with AI architects, leads, and stakeholders to design and implement generative and agentic AI solutions that address business challenges.
Architect advanced context engineering strategies — context layering, chaining, compression, pruning/offloading, and memory management — to maximize reliability, provenance, and token efficiency in production.
Design and implement advanced generative AI methods, including sophisticated prompt engineering and Retrieval-Augmented Generation (RAG).
Build and optimize RAG systems, including hybrid search, multi-vector retrieval, and re-ranking pipelines.
Design and implement knowledge graphs and Graph RAG architectures to enable multi-hop reasoning, explainability, and traceable, grounded responses for high-value business domains.
Architect agentic workflows and multi-agent systems using Google Agent Development Kit (ADK) and comparable frameworks (LangGraph, Microsoft Agent Framework, CrewAI), applying orchestration patterns such as supervisor/worker, hierarchical, and peer-to-peer.
Design robust agent harnesses — governance, constraints, feedback loops, state/session management, and execution controls that make long-running agent systems reliable and protected.
Integrate agents with tools and data via the Model Context P
📌 Lead Gen AI Engineer (Pune)
🏢 Citi
📍 Pune