GenAI Architect & Agentic AI Leader

Citi; New York (NY); Hybrid; USD 37,000 - 74,000; Full time

Job summary

Citi is seeking a Lead Gen AI Engineer (Vice President) to design and implement state-of-the-art generative and agentic AI solutions. You will craft context engineering strategies, build robust RAG pipelines, and develop knowledge graphs with Graph RAG to enable grounded, explainable responses.

You will lead multi-agent orchestration across platforms using ADK and related tools, ensuring scalable, safe production deployments.

Qualifications

• Bachelor's or master's degree in Computer Science, Data Science, AI, or a related field.
• 5–7 years of experience in AI/software development with Generative and agentic AI.
• Experience with cloud infrastructure for AI/GenAI (AWS or equivalent).

Responsibilities

• Design and implement generative and agentic AI solutions addressing business challenges.
• Architect context engineering strategies for reliable production systems.
• Build and optimize RAG systems with multi-vector retrieval and re-ranking.
• Develop knowledge graphs and Graph RAG for multi-hop retrieval and explainability.
• Create agentic workflows using Google ADK and similar frameworks; oversee governance and safety.

Skills

Core generative AI concepts

Prompt engineering

RAG systems

Knowledge graphs

Graph RAG

Agentic AI systems

Google ADK

LangGraph

CrewAI

OpenAI Agents SDK

Multi-agent orchestration

Harness engineering

MCP

A2A protocol

Agent observability

GenAI APIs

LangChain

LlamaIndex

NLP

Vector databases

Docker

Kubernetes

CI/CD for AI

Python

Education

Bachelor's or master's in CS/AI

Tools

Neo4j/ArangoDB

Job description

Citi is seeking a Lead Gen AI Engineer (Vice President) to design and implement state-of-the-art generative and agentic AI solutions. You will craft context engineering strategies, build robust RAG pipelines, and develop knowledge graphs with Graph RAG to enable grounded, explainable responses.

You will lead multi-agent orchestration across platforms using ADK and related tools, ensuring scalable, safe production deployments.