Data Science and Analytics · Tampa, FL

Hybrid Full-time

Senior AI Engineer, Python and Agentic Systems Vice President

Citi · Tampa, FL · Posted Nov 17, 2026

This posting comes from Citi. Confirm the details on their site before applying.

Overview

As a Senior AI Engineer specializing in Python and agentic systems, you will architect the generative and agentic AI solutions that power Citi's Controls Technology platform, working at the frontier of context engineering, retrieval systems, and multi-agent orchestration. You will design production-grade AI systems that are grounded, reliable, and built to operate at enterprise scale, partnering with AI architects, engineering leads, and business stakeholders across one of the world's most complex financial institutions.

Responsibilities

  • Design and build generative and agentic AI solutions in Python that solve real business problems across Citi's Controls Technology platform.
  • Architect context engineering strategies, including context layering, chaining, compression, and memory management, to keep production AI systems reliable and token-efficient.
  • Build and optimize Retrieval-Augmented Generation systems using hybrid search, multi-vector retrieval, and re-ranking pipelines.
  • Design knowledge graphs and Graph RAG architectures that enable multi-hop reasoning and traceable, grounded responses for high-value business domains.
  • Architect multi-agent systems using Google Agent Development Kit and frameworks such as LangGraph, Microsoft Agent Framework, and CrewAI.
  • Build agent harnesses that combine governance, feedback loops, and execution controls to keep long-running agent systems safe and reliable.
  • Connect agents to tools and data through the Model Context Protocol and coordinate inter-agent collaboration through the Agent2Agent protocol.
  • Mentor engineers through code reviews and technical guidance while promoting ethical AI practices and compliance standards.

Requirements

  • Brings 6+ years of experience in applications development or systems analysis, including hands-on software programming.
  • Deep knowledge of foundation models, LLMs, embeddings, tokenization, and context-window management, combined with advanced prompt engineering and context engineering skills.
  • Proven experience building RAG systems, covering chunking strategies, hybrid search, multi-vector retrieval, and knowledge graph or Graph RAG pipelines using tools such as Neo4j or ArangoDB.
  • Hands-on experience building agentic systems with Google ADK or comparable frameworks such as LangGraph, Microsoft Agent Framework, CrewAI, or OpenAI Agents SDK, including tool calling, planning, and memory management.
  • Strong grasp of multi-agent orchestration patterns and agent interoperability protocols, including the Model Context Protocol and the Agent2Agent protocol, along with experience in agent observability and evaluation.
  • Strong Python skills across data preprocessing, document ingestion, API development, NLP techniques, vector databases, and cloud infrastructure such as AWS, Docker, Kubernetes, and CI/CD pipelines.
  • A Bachelor's or Master's degree in Computer Science, Data Science, AI, or a related field, with a solid understanding of AI compliance and guardrails and clear communication across technical and non-technical audiences.

Benefits

  • Work in a hybrid model with three days in the office and two days working remotely, balancing flexibility with in-person collaboration.
  • Take on complex, large-scale AI engineering challenges that directly strengthen Citi's Controls Technology platform.
  • Deepen your expertise in generative and agentic AI through ongoing learning and development opportunities.
  • Collaborate with AI architects and engineers across a global organization, broadening your view of enterprise-scale technology.
  • Build long-term financial wellbeing through competitive compensation and benefits.
  • Gain real influence over how agentic AI systems are architected and governed within a regulated, global enterprise.

Great fits start here.

Whether you're looking for your next role or your next team member, give people and possibilities a place to meet.