Lead Agentic AI Engineer

Citi is seeking a Lead Agentic AI Engineer to design, develop, and integrate Generative AI and agentic AI solutions for the Controls Technology platform. The role focuses on building robust agentic applications on top of pre-trained or hosted foundation models, with emphasis on reliability, provenance, and token-efficient context handling. This position is based in Irving, TX on an onsite basis.

The Lead Agentic AI Engineer will partner with AI architects, leads, and stakeholders to turn business challenges into production-ready generative and agentic systems, including advanced context engineering, RAG, knowledge graphs, and multi-agent orchestration. The work also includes integration into production environments, ongoing optimization for real-time and streaming use cases, and mentoring across the engineering team.

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, 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, including hybrid search, multi-vector retrieval, and re-ranking pipelines.
• Design and implement knowledge graphs and Graph RAG architectures to support 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 such as LangGraph, Microsoft Agent Framework, and CrewAI, applying orchestration patterns including supervisor/worker, hierarchical, and peer-to-peer.
• Design robust agent harnesses, including governance, constraints, feedback loops, state/session management, and execution controls for reliable and safe long-running agents.
• Integrate agents with tools and data via Model Context Protocol (MCP) and coordinate inter-agent collaboration and task delegation through Agent2Agent (A2A).
• Support production integration for GenAI and agentic applications, ensuring robust deployment, scalability, observability, and maintainability.
• Contribute to development and optimization of real-time and streaming AI solutions.
• Stay current with latest 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 support a culture of 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 (for example, using Neo4j or ArangoDB) for relationship-aware, multi-hop retrieval.
• Proven experience building agentic AI systems with Google ADK and/or comparable frameworks such as LangGraph, Microsoft Agent Framework, CrewAI, and 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) for production systems.
• Proficiency with major GenAI APIs including OpenAI, Gemini, Claude, and orchestration frameworks such as LangChain and LlamaIndex.
• Strong skills in NLP (NER, dependency parsing, text classification, topic modeling).
• Proficiency with vector databases and embedding models for large-scale retrieval.
• Experience with Docker, Kubernetes, and CI/CD pipelines for AI/agentic applications.
• Solid understanding of AI compliance, guardrails, and responsible AI practices.
• Strong skills in Python and experience with data preprocessing, document ingestion, and API development.
• Strong collaboration skills to work effectively in cross-functional teams.
• Analytical and proactive approach to problem-solving.
• Clear communication skills for both technical and non-technical audiences.
• Eagerness to learn, innovate, and mentor less experienced developers.
• Bachelor’s or master’s degree in Computer Science, Data Science, AI, or a related field.
• 5 to 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.

Technologies

• Google Agent Development Kit (ADK), LangGraph, Microsoft Agent Framework, CrewAI
• Prompt engineering, Retrieval-Augmented Generation (RAG), context engineering
• Knowledge graphs, Graph RAG
• Model Context Protocol (MCP), Agent2Agent (A2A)
• OpenTelemetry, LangChain, LlamaIndex, OpenAI Agents SDK
• OpenAI, Gemini, Claude
• Neo4j, ArangoDB, vector databases
• Docker, Kubernetes, CI/CD
• Python, AWS, embeddings, LLMs

Compensation and Logistics

• Employment type: Full time
• Location: Irving, Texas, United States (onsite)
• Salary: USD 125,760 - 188,640 per year
• Job family: Technology
• Job family group: Applications Development
• Anticipated posting close date: Sep 24, 2026

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)