Get Started
Hunting for you, 24x7Get the iPhone app

Your hunt runs in your pocket, and tells you the moment a strong match opens.

Download on theApp Store
CitiPosted in November 2026

Risk Modeling Solutions - Full-stack GenAI - Assistant Vice President

Who we'd reach at CitiFound and reached by Power Apply
Best leadTeam lead

Runs the team day to day

Recruiter

In-house, owns the opening

Recent hire

Joined the team recently

Power Apply

From your own Gmail and LinkedIn.

About the role

This is a full-time, senior engineering role at Citi on the Risk Modeling Solutions team, building generative AI applications for risk management work. It suits engineers with about six years of combined software and data science or machine learning experience who can build agentic systems and RAG pipelines in Python. The AI Lab turns quantitative analysis into automated reporting and decision tools, so the work sits close to model risk and governance requirements.

What you’ll do

  • Design multi-agent workflows that reason, plan and act, using LangGraph, CrewAI, Google ADK or similar frameworks.
  • Translate risk problems into technical requirements and build end-to-end AI solutions for them.
  • Build retrieval pipelines, memory layers and tool-use chains with LangChain.
  • Write scalable Python microservices and REST APIs in FastAPI that expose AI capabilities.
  • Construct RAG pipelines covering document ingestion, embeddings and vector search with Azure AI Search or Pinecone.
  • Package AI services in Docker and deploy them on Kubernetes, contributing to CI/CD.
  • Instrument workflows with Langfuse for tracing and maintain evaluation harnesses.

What they’re looking for

  • About six years of professional experience blending software development with data science or machine learning.
  • Expert Python skills and a record of building scalable backend services and APIs, FastAPI preferred.
  • Deep hands-on work with several agent frameworks such as LangChain, LangGraph, CrewAI, AutoGen or Semantic Kernel.
  • Experience with RAG systems and vector databases such as OpenSearch, Pinecone or Weaviate.
  • Containerized AI systems on AWS, Azure or GCP using Docker and Kubernetes.
  • MLOps practice covering CI/CD, observability and evaluation for LLM systems.
  • Understanding of AI risk, safety and enterprise governance requirements.
  • Solid background in ML, deep learning and NLP, including transformer architectures.

Nice to have

  • Experience leading the design of LLM evaluation harnesses for automated release validation.
  • Deep experience with Langfuse or similar AI observability and tracing platforms.
  • Hands-on work with AWS Bedrock, Azure AI Foundry or GCP Vertex AI.
  • Knowledge of GraphRAG and multi-hop retrieval strategies.
  • AWS certifications such as Solutions Architect or AI/ML Specialty.
  • Background in financial services or another highly regulated industry.

Skills

Questions about this role

How many years of experience do I need?

The listing asks for six years of professional experience across software development and data science or machine learning.

Is this a full-time role?

Yes, the listing is for full-time work.

Which frameworks should I know?

The listing names LangChain, LangGraph, CrewAI, AutoGen and Semantic Kernel, along with FastAPI for services.