C

Citi

Runs banking and payments for global clients

Software Engineer Gen AI Assistant Vice President

AI Application Engineering +1Confirmed live in the last 24 hours
Full-timeIrving, TX, USAHybrid

About the Job

Requirements

  • Strong computer science fundamentals, including data structures, algorithms and complexity, operating systems, networking, and relational database design and optimization.
  • Advanced Python skills, including asynchronous programming, typing, and dependency management, plus clean coding, automated testing, version control, and continuous integration and continuous delivery practices.
  • Hands-on experience developing large language model applications, including prompt engineering, tool and function calling, structured outputs, and multi-agent frameworks.
  • Practical retrieval-augmented generation pipeline experience using vector databases and embedding-based retrieval, plus familiarity with structured large language model and agent output evaluation methods.
  • Experience integrating AI systems with external tools and documentation through structured interfaces such as Model Context Protocol, and working knowledge of Docker and Kubernetes or OpenShift.
  • A bachelor's or master's degree in Computer Science, Software Engineering, or a related technical discipline.
  • Four to seven years of professional software engineering experience building scalable backend or full-stack distributed systems.
  • At least three years of experience in artificial intelligence or machine learning, including at least two years specifically in generative AI, large language models, retrieval-augmented generation, agentic workflows, or Model Context Protocol.
  • Advanced Python proficiency, prompt engineering, Google Agent Development Kit, LangChain, LangGraph, and custom state machines.
  • In-depth implementation knowledge of Model Context Protocol clients and servers.
  • Knowledge of GraphRAG, LightRAG, RAPTOR, hybrid search using BM25 and dense embeddings, cross-encoder reranking models, and chunking strategies.
  • Knowledge of Python backend frameworks FastAPI, Flask, and Django, and Java frameworks Spring Boot and Spring Cloud.
  • Knowledge of React, including hooks, state management, and component architecture; TypeScript or JavaScript; and responsive user interface design.
  • Knowledge of relational database systems including Oracle and PostgreSQL, including schema design, indexing, query optimization, and connection management.
  • Knowledge of Neo4j and Cypher queries, pgvector, Pinecone, and Milvus.
  • Knowledge of Redis and Apache Kafka.
  • Strong analytical skills and the ability to communicate complex technical concepts clearly.
  • Knowledge of core data structures such as trees, graphs, hash maps, queues, and heaps, and Big-O time and space analysis.
  • Understanding of object-oriented and functional programming, SOLID principles, clean code, design patterns, separation of concerns, and dependency injection.
  • Understanding of distributed systems concepts including the CAP theorem, event-driven architectures, asynchronous messaging with Kafka or RabbitMQ, idempotency, distributed transactions, and database isolation levels.
  • Comprehensive testing knowledge across unit testing with pytest, unittest, JUnit, and Mockito; integration testing; contract testing; mocking; test-driven development; and large language model evaluation and regression testing.
  • Proficiency with Git workflows, automated CI/CD pipelines, Docker, Kubernetes or OpenShift, and infrastructure as code.
  • Hands-on experience with distributed tracing, structured logging, and metrics using OpenTelemetry, Prometheus, Grafana, and ELK or Loki to track large language model token latency and tool calls.
  • Understanding of OWASP Top 10 and OWASP Top 10 for large language models; secure API authentication and authorization using OAuth2, OIDC, mTLS, and RBAC; secrets management; and data sanitization and personally identifiable information redaction.
  • Experience with Google Agent Development Kit or comparable orchestration frameworks, observability tooling such as Langfuse and Prometheus, and distributed tracing.
  • Exposure to Go and front-end development with React and TypeScript, including server-sent events streaming.
  • Experience with ChromaDB or pgvector, HDBSCAN clustering, HashiCorp Vault, and SSO or JWT authentication patterns.
  • Experience with GitHub, JIRA, and documentation-search integrations for backlog and pull request workflows.

Responsibilities

  • Build and maintain production AI agents for product analysis, requirements capture, user interface prototyping, backlog generation, and automated code implementation with pull request creation.
  • Implement multi-agent workflows using Google Agent Development Kit, including sub-agent orchestration, human-in-the-loop approval gates, and agent-to-agent messaging.
  • Integrate Gemini and Anthropic Claude into agent pipelines through enterprise gateways, applying prompt engineering and structured tool and function calling.
  • Connect agents to enterprise systems, including engineering and AI product documentation, JIRA, and GitHub, using Model Context Protocol-style tool interfaces.
  • Build retrieval-augmented generation pipelines using vector search, embeddings, and clustering to ground agent responses in enterprise context.
  • Build evaluation harnesses, including large language model-as-judge and parallel jury methods, to measure faithfulness, relevance, hallucination rate, and task completion.
  • Write advanced asynchronous Python and build well-documented FastAPI services backed by persistent PostgreSQL session state.
  • Apply data structures, algorithms, and complexity analysis to make orchestration and retrieval logic efficient at scale.
  • Instrument services for observability, maintain CI/CD and containerized deployments, apply secure coding and guardrail practices, and write unit, integration, and end-to-end tests for every change.
  • Lead the design, implementation, and lifecycle of custom AI platform components; build highly available microservices and full-stack applications using Python, Java with Spring Boot, and modern front-end frameworks such as React for internal fine-tuning control planes, inference gateways, and experiment-tracking dashboards.
  • Code, evaluate, and optimize multi-tenant intelligent agents using modular orchestration patterns such as ReAct and ReWOO, leveraging Google Agent Development Kit, LangGraph, and LangChain.
  • Develop and enforce clean, decoupled enterprise integration architectures.
  • Apply clean architecture, domain-driven design, and SOLID principles across Python and Java codebases; implement Strategy, Factory, Adapter, Circuit Breaker, and Saga design patterns for modularity and fault isolation.
  • Write concurrent and asynchronous code using Python asyncio, multithreading, Java CompletableFuture and virtual threads, and connection pooling to support streaming tokens, parallel agent tool execution, and high-concurrency inference loops.
  • Design systems for high availability, fault tolerance, and graceful degradation, including rate limiting, token bucket algorithms, exponential-backoff retry policies, and distributed caching such as Redis.
  • Design clean, versioned, idempotent RESTful APIs, gRPC endpoints, and WebSockets for real-time streaming outputs, following OpenAPI or Swagger specifications.
  • Build and optimize data-ingestion and retrieval pipelines for GraphRAG, LightRAG, and hierarchical summary trees such as RAPTOR.
  • Integrate graph databases such as Neo4j and vector databases such as pgvector, Pinecone, and Milvus for semantic, hybrid, and relational data retrieval.
  • Design deterministic large language model system instructions, classification logic, and semantic-routing trees to prevent intent collisions and hallucinations in complex multi-step workflows.
  • Collaborate directly with subject matter experts to translate business and domain logic into automated, production-ready, agent-driven software.
  • Partner with user interface engineers and core API platform teams to connect backend agent logic with user-facing React applications and existing enterprise service layers.

Desired Qualifications

  • Direct experience with Google Agent Development Kit or comparable orchestration frameworks, observability tools such as Langfuse and Prometheus, and distributed tracing.
  • Exposure to Go and front-end development with React and TypeScript, including server-sent events streaming.
  • Experience with ChromaDB or pgvector, HDBSCAN clustering, HashiCorp Vault, and SSO or JWT authentication patterns.
  • Experience with GitHub, JIRA, and documentation-search integrations for backlog and pull request workflows.

About the Company

Citi

Runs banking and payments for global clients

Citi runs banking, investment and payment services for companies, governments and individuals around the world. Its global network connects institutions with local banking systems, while its US consumer business sells credit cards and deposit accounts. Corporate clients use Citi to manage cash, finance trade and raise capital, and investors use its trading, custody and wealth services to hold and manage assets. The bank earns interest on loans and fees from payments, securities transactions, financial advice and account services. Citi traces its banking roots to 1812; the Citigroup holding company was formed in 1998, and its headquarters are in New York City.

Company size
10,001+
Company stage
IPO
Headquarters
New York City, New York
Founded
1812

Recently Posted Jobs

Explore more opportunities at Citi

See more jobs