Senior AI Engineer - Vice President

Citibank (Switzerland) AG; Pune District; On-site; Confidential; Full time

Job summary

Citibank (Switzerland) AG seeks senior AI/Software Architect to design and lead advanced agentic systems for Funds Transfer Pricing and Financial Hedging domains. You will mentor engineers, drive AI strategy, and ensure scalable, low-latency solutions.

Role requires deep experience with Python/SQL, LangChain, LlamaIndex, multi-agent frameworks, and practical LLM integration. Collaborative leadership in a fast-paced financial tech environment is essential.

Qualifications

• 12+ years of professional experience in software development and system design.
• Proficiency in Python and SQL, with production-quality agentic AI development experience.
• Experience architecting multi-agent systems using frameworks like Google ADK, LangGraph, AutoGen or CrewAI.

Responsibilities

• Design and orchestrate complex multi-agent systems with collaborative autonomous agents.
• Design and implement advanced planning and reasoning using knowledge graphs and rule-based methods.
• Develop resilient agent architectures with feedback-driven improvement and dynamic replanning.
• Integrate LLMs, predictive models, and reasoning frameworks to expand capabilities.
• Design and optimize Retrieval-Augmented Generation (RAG) architectures and retrieval pipelines.
• Develop APIs and microservices to integrate AI capabilities with enterprise apps.

Skills

Python

SQL

LangChain

LlamaIndex

LangGraph

AutoGen

CrewAI

Google ADK

Memory systems

Vector DBs

LLMs

Prompt engineering

Education

Bachelor's degree in CS

Master's degree preferred

Tools

Java

Job description

Responsibilities

• Advanced Agent and Model Development

  Design and orchestrate complex multi-agent systems where autonomous agents collaborate, coordinate, negotiate, and delegate tasks to solve business problems that exceed the capabilities of a single agent.

  Design and implement advanced planning and reasoning capabilities using techniques such such as knowledge graphs for relationship-aware reasoning, rule-based and symbolic reasoning for deterministic business decisions, and planning/search algorithms to execute complex multi-step workflows reliably and efficiently.

  Develop resilient and adaptive agent architectures with mechanisms for feedback-driven improvement, error recovery, self-correction, and dynamic replanning to enhance reliability, accuracy, and task completion rates.

  Integrate large language models (LLMs), predictive models, and reasoning frameworks to expand agent capabilities, improve decision quality, and support complex business workflows.

  Design and optimize Retrieval-Augmented Generation (RAG) architectures, including embedding strategies, vector databases, retrieval pipelines, reranking, and context management to maximize response accuracy and relevance.

  Design and develop APIs, tools, and microservices that enable seamless integration of AI capabilities with enterprise applications, databases, and business platforms.

• Performance and Optimization

  Optimize AI systems for low latency and high throughput. Implement advanced techniques such as response streaming and caching, while ensuring cost-effectiveness through strategic model selection and rigorous token usage optimization.

• Technical Leadership and Strategy

  AI Research and Strategy: Act as a subject matter expert, driving the technical strategy for AI within the Funds Transfer Pricing and Financial Hedging domains by staying abreast of state-of-the-art research and identifying opportunities for innovation.

  Mentorship and Technical Guidance: Mentor junior engineers on AI best practices and provide technical leadership across multiple project teams, fostering a culture of engineering excellence.

Required Qualifications & Skills

• 12+ years of professional experience in software development and system design, with a proven track record of delivering large-scale systems. Professional experience in software development and system design.
• Proficiency in Python and SQL, with experience in production-quality Agentic AI development; applied experience with frameworks like LangChain, LlamaIndex, or equivalents.
• A proven track record of architecting multi-agent systems using frameworks like Google ADK, LangGraph, AutoGen or CrewAI. This includes hands-on experience with planning/reasoning, memory systems, MCP and Vector DBs.
• Practical knowledge of LLMs and their application within agentic architectures, including API design and integration for AI services.
• Demonstrated mastery of Prompt and Context Engineering, including the ability to structure and compress information for optimal model performance.

Beneficial Qualifications & Skills

• Experience working in the financial services industry.
• Proficiency in Java as an additional programming language.
• Education Bachelor's degree/University degree in Computer Science or a related field. Master's degree preferred.

Job Family Group: Technology

Job Family: Applications Development

Time Type: Full time

Citi is an equal opportunity employer, and qualified candidates will receive consideration without regard to their race, color, religion, sex, sexual orientation, gender identity, national origin, disability, status as a protected veteran, or any other characteristic protected by law. If you are a person with a disability and need a reasonable accommodation to use our search tools and/or apply for a career opportunity review Accessibility at Citi. View Citi's EEO Policy Statement and the Know Your Rights poster.