Apps Development Group Manager - Senior Vice President

Citigroup; Tampa (FL); On-site; USD 150,000 - 230,000; Full time

Job summary

Citigroup seeks a Digital Software Engineering Lead Analyst to design and implement enterprise-grade Agentic AI solutions, integrating data across systems and scaling with fault tolerance. You will drive AI system blueprints, data pipelines, and RAG architectures while collaborating with Data Engineering, Enterprise Platforms, and Product teams.

You will lead hands-on design, embedding best practices in ML/AI, deployment, and governance, ensuring secure and compliant AI workloads in a dynamic

Qualifications

• 10+ years in software/AI engineering or architecture.
• Proven enterprise AI systems deployments in production.
• Strong ML/LLM foundations and RAG experience.
• Hands-on with Python and AI tooling.

Responsibilities

• Design and build agentic AI systems with multi-agent orchestration.
• Architect fault-tolerant, scalable AI solutions and end-to-end blueprints.
• Lead data integration, pipelines, and knowledge orchestration for LLM workloads.
• Develop GenAI apps with containerized cloud infrastructure and MLOps pipelines.
• Mentor engineers and influence platform strategy on GenAI trends.

Skills

ML/AI engineering

LLMs

RAG architectures

Python

Data pipelines

Cloud engineering

MLOps

Agentic systems

Education

Bachelor's degree in CS/related field

Tools

LangChain

LangGraph

Google_ADK

OpenAI

Pinecone

PGVector

MongoDB Atlas Vector Search

Neo4j

Milvus

Kubernetes

Docker

Helm

GitHub Actions

Jenkins

Azure DevOps

ArgoCD

OpenShift

Job description

The Digital Software Engineering Lead Analyst is a strategic technical leader responsible for designing and engineering enterprise grade Agentic AI solutions capable of integrating data from multiple heterogeneous systems and operating reliably at scale.

You will act as a hands-on architect, engineer, and partner to cross functional teams-including Data Engineering, Architecture, Enterprise Platforms, and Product-defining the technical approach, AI system design, and integration patterns needed to build robustfault tolerantnt AI agents and AIdriven automation capabilities.This role requires deep technical breadth across machine learning, LLMs, data pipelines, cloud engineering, orchestration, and modern AI frameworks. The solutions you design will enable strategic automation, cognitive decisioning, and dynamic multi-agent workflows across the organization.

Key Responsibilities

AI Solution Architecture & Agentic Systems

• Design and build agentic AI systems, including autonomous agents, multiagent orchestration, tool use, and adaptive decision-making workflows.
• Architect fault tolerant, scalable AI solutions using modern agent frameworks (e.g., Google_ADK, LangGraph, LangChain , OpenAI Assistants, CrewAI, AutoGen, custom orchestrators).
• Define the end-to-end AI system blueprint, including knowledge integration, orchestration, pipelines, observability, governance, and failover strategies.
• Evaluate and select LLMs, embeddings, vector stores, and middleware best suited for complex enterprise requirements.

Data Integration & Pipeline Engineering

• Partner with engineering teams to aggregate, ingest, and harmonize data from multiple systems, including APIs, databases, internal platforms, and unstructured sources.
• Design robust data pipelines optimized for LLM workloads (e.g., chunking, metadata design, semantic indexing, retrieval strategies).
• Implement mechanisms for ensuring data freshness, quality, and fault tolerance across distributed systems.

LLM, RAG, and Generative AI Engineering

• Build advanced Retrieval-Augmented Generation (RAG) architectures, including hybrid retrieval, query planning, and retrieval optimization.
• Develop, tune, and deploy applications leveraging major LLMs (OpenAI, Gemini, Claude, Llama, Mistral, HuggingFace ecosystem).
• Engineer prompts, system instructions, and reusable prompt templates for deterministic AI behavior.
• Implement safety guardrails, evaluation pipelines, and bias/error mitigation strategies.

AI Platform Engineering & Deployment

• Develop cloudnative GenAI applications using containerized infrastructure (Kubernetes, OpenShift, Docker).
• Build and support production-grade MLOps / AIOps pipelines, including CI/CD, automated testing, monitoring, model versioning, and rollback strategies.
• Partner with engineering teams to ensure secure, compliant deployment of all AI workloads.

Technical Leadership & Collaboration

• Serve as technical SME for AI engineering patterns, solution design, and architecture.
• Mentor mid-level engineers and analysts, guiding best practices in AI build patterns and engineering quality.
• Influence product and platform strategy by providing insights on emerging GenAI and agentic technologies.

Qualification:

Experience

• 10+ years of experience in software engineering, AI/ML engineering, systems architecture, or related fields.
• Proven experience designing and deploying enterprisegrade AI Systems in production.

Required Technical Skills

Core AI/ML & GenAI Expertise

• Strong foundations in ML, NLP, embeddings, statistics, neural networks, and LLMs.
• Extensive handson experience with LLMs: Gemini, OpenAI, Claude, Mistral, Llama, opensource models, etc.
• Deep expertise in RAG architectures, including retrieval optimization, vector search, and semantic data modeling.
• Experience building agentic AI using Google_ADK or langGraph

Programming & Data Engineering

• Strong proficiency in Python and libraries such as: Pandas, NumPy, scikitlearn, PyTorch, TensorFlow, Transformers, FastAPI, LangChain, LlamaIndex.
• Hands-on experience with vector databases: Pinecone, PGVector, MongoDB Atlas Vector Search, Neo4j, Milvus, etc.
• Experience building pipelines for large-scale unstructured data processing.

Cloud, DevOps, & MLOps

• Strong CI/CD experience: GitLab CI, Jenkins, Azure DevOps, ArgoCD, GitHub Actions.
• Expertise deploying GenAI solutions in production using: Kubernetes, Docker, Helm, serverless runtimes, or cloud-native LLM services.
• Experience with monitoring, observability, and logging frameworks relevant for AI workloads.

Soft Skills

• Exceptional problem-solving and analytical skills.
• Ability to execute independently while operating effectively in ambiguity.
• Strong collaboration skills across engineering, architecture, and product teams.
• Deep commitment to ethics, transparency, and responsible AI usage.

Preferred Qualifications

• Experience building AI systems in regulated or enterprise environments.
• Experience using knowledge graphs, graph databases, or enterprise metadata syste