Senior LLM & Agentic AI Engineer - Assistant Vice President
Citi · Chennai · 8–11 yrs experience · Posted 2026-07-18
Tech stack: Angular, Java, Python, React
Apply on the company site · Get a referral for this role
Citi salary & ratings · Citi interview process · More live openings
About the role
We are looking for a hands-on Senior AI Engineer to design, build, and scale next-generation AI-powered digital experiences. You will work on cutting-edge Generative AI, Agentic AI, Conversational AI, and Machine Learning solutions that enhance customer engagement, automate workflows, and deliver personalized experiences at scale.
This role is ideal for engineers passionate about building production-grade AI systems using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI Agents, and modern cloud-native architectures.
Responsibilities: - Generative AI & Agentic AI
- Design and deploy enterprise-grade GenAI applications using GPT, Claude, Gemini, or equivalent LLMs.
- Build Agentic AI solutions using frameworks such as LangChain, LangGraph, CrewAI, or similar.
- Develop multi-agent systems to automate customer journeys and business workflows.
- Implement advanced prompt engineering, evaluation frameworks, and guardrails to improve AI response quality.
- RAG & Knowledge Systems
- Design and optimize Retrieval-Augmented Generation (RAG) architectures.
- Integrate vector databases and enterprise knowledge repositories.
- Improve retrieval accuracy, response relevance, and grounding of AI-generated content.
- Software Engineering Build scalable backend services and APIs using Java and/or Python.
- Develop cloud-native microservices and integrate AI capabilities into customer-facing applications.
- Collaborate with architects, product managers, and business stakeholders to deliver high-impact solutions.
- AI Operations & Governance
- Monitor model performance, latency, and operational costs.
- Implement AI governance, observability, and responsible AI practices.
- Optimize LLM usage and inference costs in production environments.
- Required Skills Must Have
- 8-11 years of software engineering experience.
- 2+ years of hands-on experience building GenAI or LLM-powered applications.
- Strong experience with:
- GPT, Claude, Gemini, or similar LLMs
- LangChain, LangGraph, CrewAI, or AI Agent frameworks
- Retrieval-Augmented Generation (RAG)
- Vector databases Prompt Engineering
- Strong programming skills in Java and/or Python.
Qualifications: - building REST APIs and microservices.
- Familiarity with cloud platforms and modern software development practices.
- Nice to Have
- MLOps experience (deployment, monitoring, model lifecycle management).
- with recommendation engines or conversational AI platforms.
- of financial services, wealth management, or digital banking.
- with React, Angular, or modern frontend frameworks.
- Build scalable AI-powered digital experiences used by millions of customers.
- Deliver production-ready Agentic AI and GenAI solutions.
- Improve customer engagement, automation, and operational efficiency through AI innovation.
- Drive adoption of emerging AI technologies across the organization.
Qualifications
- building REST APIs and microservices.
- Familiarity with cloud platforms and modern software development practices.
- Nice to Have
- MLOps experience (deployment, monitoring, model lifecycle management).
- with recommendation engines or conversational AI platforms.
- of financial services, wealth management, or digital banking.
- with React, Angular, or modern frontend frameworks.
- Build scalable AI-powered digital experiences used by millions of customers.
- Deliver production-ready Agentic AI and GenAI solutions.
- Improve customer engagement, automation, and operational efficiency through AI innovation.
- Drive adoption of emerging AI technologies across the organization.
Responsibilities
- Generative AI & Agentic AI
- Design and deploy enterprise-grade GenAI applications using GPT, Claude, Gemini, or equivalent LLMs.
- Build Agentic AI solutions using frameworks such as LangChain, LangGraph, CrewAI, or similar.
- Develop multi-agent systems to automate customer journeys and business workflows.
- Implement advanced prompt engineering, evaluation frameworks, and guardrails to improve AI response quality.
- RAG & Knowledge Systems
- Design and optimize Retrieval-Augmented Generation (RAG) architectures.
- Integrate vector databases and enterprise knowledge repositories.
- Improve retrieval accuracy, response relevance, and grounding of AI-generated content.
- Software Engineering Build scalable backend services and APIs using Java and/or Python.
- Develop cloud-native microservices and integrate AI capabilities into customer-facing applications.
- Collaborate with architects, product managers, and business stakeholders to deliver high-impact solutions.
- AI Operations & Governance
- Monitor model performance, latency, and operational costs.
- Implement AI governance, observability, and responsible AI practices.
- Optimize LLM usage and inference costs in production environments.
- Required Skills Must Have
- 8-11 years of software engineering experience.
- 2+ years of hands-on experience building GenAI or LLM-powered applications.
- Strong experience with:
- GPT, Claude, Gemini, or similar LLMs
- LangChain, LangGraph, CrewAI, or AI Agent frameworks
- Retrieval-Augmented Generation (RAG)
- Vector databases Prompt Engineering
- Strong programming skills in Java and/or Python.