Lead Agentic AI Engineer

Citi; Irving (TX); On-site; USD 126,000 - 189,000; Full time

Benefits offered by this job

Medical coverage

Dental and vision coverage

401(k) plan

Life insurance

Disability insurance

Wellness programs

Paid time off

Job summary

Citi in Irving, TX is seeking a hands-on AI software professional to lead the design and delivery of GenAI and agentic AI capabilities for Citi's Controls Technology platform.

You will architect robust agentic applications on top of foundation models, applying context engineering, RAG, knowledge graphs, and multi-agent orchestration patterns. This is an onsite role with a strong focus on scalable deployment and governance.

Qualifications

• Deep expertise in foundation models, embeddings, tokenization, and context-window management.
• Proven history building RAG systems with multi-vector retrieval and prompt engineering.
• Experience designing knowledge graphs and Graph RAG architectures.
• Hands-on with Google ADK, LangGraph, CrewAI, and comparable frameworks.
• Strong Python skills and experience with API development and data preprocessing.

Responsibilities

• Collaborate with AI architects and stakeholders to design generative and agentic AI solutions.
• Architect context engineering strategies for reliability, provenance, and token efficiency.
• Develop advanced prompt engineering and RAG methods for production use cases.
• Build and optimize RAG systems with hybrid search and multi-vector retrieval.
• Design knowledge graphs and Graph RAG pipelines for multi-hop reasoning.
• Architect agentic workflows and multi-agent systems with ADK and related frameworks.
• Develop agent harnesses for governance, safety, and execution controls.
• Integrate agents with tools/data via MCP and promote inter-agent collaboration (A2A).
• Support production deployment, observability, and maintainability of GenAI apps.
• Mentor juniors and stay current with advances in generative AI and agentic tech.

Skills

Generative AI

Agentic AI

Python

NLP

Context engineering

RAG

Knowledge graphs

Multi-agent systems

API development

Cloud (AWS)

Education

Bachelor's or Master's in CS/Data Science/AI

Tools

OpenAI APIs

LangChain

LlamaIndex

Neo4j

ArangoDB

Google ADK

Kubernetes

Docker

CrewAI

LangGraph

Job description

Work onsite in Irving, TX and lead the design and delivery of production-ready Generative AI and agentic AI capabilities for Citi's Controls Technology platform.

In this role, you will architect robust agentic applications on top of pre-trained or hosted foundation models, applying context engineering, RAG, knowledge graphs, and multi-agent orchestration patterns. You will also contribute to deployment practices that support scalability, observability, and maintainability for real-world business use cases.

Responsibilities

• Collaborate with AI architects, leads, and stakeholders to design and implement generative and agentic AI solutions for business challenges.
• Architect advanced context engineering strategies, including context layering, chaining, compression, pruning/offloading, and memory management, to improve 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 with hybrid search, multi-vector retrieval, and re-ranking pipelines.
• Design knowledge graphs and Graph RAG architectures to support multi-hop reasoning, explainability, and traceable, grounded responses in high-value domains.
• Architect agentic workflows and multi-agent systems using Google Agent Development Kit (ADK) and comparable frameworks such as LangGraph, Microsoft Agent Framework, and CrewAI, applying orchestration patterns like supervisor/worker, hierarchical, and peer-to-peer.
• Develop robust agent harnesses for governance, constraints, feedback loops, state/session management, and execution controls to support long-running agent reliability and safety.
• Integrate agents with tools and data via Model Context Protocol (MCP) and orchestrate inter-agent collaboration using the Agent2Agent (A2A) protocol.
• Support production integration of GenAI and agentic applications, ensuring robust deployment, scalability, observability, and maintainability.
• Contribute to the development and optimization of real-time and streaming AI solutions.
• Stay current with advances in generative and agentic AI and share knowledge with the team.
• Ensure adherence to ethical AI guidelines, guardrails, agent isolation/sandboxing, data privacy, and compliance standards.
• Mentor junior team members, provide code reviews, and foster technical excellence.

Requirements

• Deep, hands-on expertise in core generative AI concepts, including foundation models, LLMs, embeddings, tokenization, and context-window management.
• Advanced skills in prompt engineering and context engineering, including familiarity with prompt design tools/frameworks and dynamic context orchestration.
• Strong experience building RAG systems, including chunking strategies, hybrid search, and multi-vector retrieval.
• Practical experience designing knowledge graphs and Graph RAG pipelines (example tools include Neo4j or ArangoDB).
• Proven experience building agentic AI systems with Google ADK and/or comparable frameworks (LangGraph, Microsoft Agent Framework, CrewAI, OpenAI Agents SDK), including tool/function calling, planning, and memory.
• Strong grasp of multi-agent orchestration patterns (supervisor/worker, hierarchical, peer-to-peer) and harness engineering (governance, feedback loops, execution controls, agent isolation/sandboxing).
• Hands-on experience with agent interoperability protocols, including MCP for tool/data access and A2A for inter-agent collaboration.
• Experience with agent observability and evaluation (for example, tracing and OpenTelemetry-based tooling).
• Proficiency with major GenAI APIs (OpenAI, Gemini, Claude, etc.) and orchestration frameworks such as LangChain and LlamaIndex.
• Strong skills in NLP (NER, dependency parsing, text classification, topic modeling) and familiarity with vector databases and embedding models.
• Experience with containerization (Docker), orchestration (Kubernetes), and CI/CD pipelines for AI/agentic applications.
• Solid understanding of AI compliance, guardrails, and responsible AI practices.
• Strong Python skills, including data preprocessing, document ingestion, and API development.
• Strong collaboration skills across cross-functional teams; clear communication for technical and non-technical audiences.
• Analytical and proactive problem-solving approach, with eagerness to learn, innovate, and mentor.
• 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, including significant experience in Generative AI and agentic AI.
• Demonstrated portfolio of successful AI-driven projects in a business environment.
• Experience working with AWS (or equivalent) cloud infrastructure for AI/GenAI.

Benefits

• Medical, dental & vision coverage
• 401(k)
• Life, accident, and disability insurance
• Wellness programs
• Planned time off (vacation)
• Unplanned time off (sick leave)
• Paid holidays
• Discretionary and formulaic incentive and retention awards (for eligible employees)

Employment type: Full time

Primary location: Irving, Texas, United States

Salary range: $125,760.00 - $188,640.00 per year

Posting close date: Sep 24, 2026