Senior Application Development Lead - Generative AI Gen AI, Vice President - Citi

About the Role

Discover your future at Citi
Working at Citi is far more than just a job. A career with us means joining a team of approximately 219,000 dedicated people from around the globe. At Citi, you'll have the opportunity to grow your career, give back to your community and make a real impact.

Job Overview
Senior Application Development Lead - Generative AI (Gen AI)

Are you looking for a career move that will put you at the heart of a global financial institution? Then bring your skills in analysis, application development, problem solving and communication to Source t o Pay Solutions Technology group .

By Joining Citi, you will become part of a global organisation whose mission is to serve as a trusted partner to our clients by responsibly providing financial services that enable growth and economic progress.

Team/Role Overview

Source t o Pay Solutions T echnology group is part of COO ( Citi Operating Office ) T echnology o rganization supporting C iti Operating Office business function and its enterprise - wide transformation agenda to ac hieve improvements across risk management, controls, data governance, AI adoption, and process re - engineering by delivering scalable, secure, and modern technology solutions. Based in Belfast , the team partners closely with businesses and technology stakeholders to build, manage, and modernize multiple Source to Pay applications , playing a key role in translating strategic transformation priorities into measurable operational outcomes.

What you'll do

• Senior Application Development Lead (Gen AI) is a senior level position responsible for

• Set technical direction for Gen AI adoption across multiple applications or teams, defining reusable patterns, reference architectures, and best practices aligned with enterprise standards.

• Design, integrate, and evolve Gen AI capabilities (LLMs, APIs, agentic workflows, automation) in business - critical applications, focusing on clear value, reliability, and responsible usage

• Own end - to - end delivery of Gen AI enabled features , from solution design and implementation through production rollout, support, and continuous improvement

• Collaborate daily with global and regional technology and business teams to deliver against regulatory, risk, and transformation priorities

• Apply agile engineering practices , leveraging iterative delivery, pragmatic architectural decisions, and emerging Gen AI/agentic tooling to accelerate outcomes

• Provide technical leadership and mentorship through hands - on development, code reviews, and design guidance, raising the overall engineering bar

• Ensure solutions meet Citi standards for security, stability, resilience, and operational control, working closely with architecture, risk, and production support teams

• Continuously assess and improve system quality , balancing performance, cost, accuracy, and user experience in production Gen AI applications

• Deep expertise in Large Language Models (LLMs) , including commercial and open - source models (e.g., OpenAI, Gemini, Claude, Llama), and selecting the right model for use case, cost, and performance constraints

• Hands - on experience building Gen AI applications using modern frameworks such as LangChain , LangGraph , LlamaIndex , and Hugging Face, including agentic and multi - step workflows

• Proven experience designing and implementing Retrieval - Augmented Generation (RAG) systems , including vector databases ( pgvector , Pinecone, Weaviate , FAISS, etc.) and advanced retrieval strategies (hybrid search, re - ranking , metadata filtering)

• Strong understanding of prompt engineering, workflow design, and Gen - AI optimization , balancing latency, cost, quality, and accuracy trade - offs in production systems

• Solid grounding in ML/DL concepts , with hands - on experience applying frameworks such as PyTorch and/or TensorFlow , including embeddings and model fine - tuning where appropriate

• Experience deploying and operating production Gen AI systems , leveraging Docker, cloud - native architecture, production APIs, and monitoring/observability tools , with an emphasis on reliability and scalability

• S trong hands - on software engineering skills , including Python, FastAPI , async programming patterns , and building high - performance AI - powered APIs

• Understanding of