Senior Generative AI Developer

Citigroup, Inc.
New York, NY, United States
2 days ago

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Experience level
Expert
Experience required
2 years minimum
Working hours
Regular working hours

Tech stack

Application Programming Interfaces (APIs) Artificial Intelligence Amazon Web Services Automation of Tests Microsoft Azure Cloud Computing Code Review Encodings Continuous Integration Information Engineering Python (Programming Language) NoSQL
+20 more
Performance Tuning Search Technologies Software Engineering SQL Databases Google Cloud Flask (Web Framework) Delivery Pipeline Large Language Models Multi-Agent Systems Prompt Engineering Generative AI Git Fastapi AI Platforms Kubernetes Machine Learning Operations Api Design GPT Data Pipelines Docker

Job description

Experteer Overview In this hands-on role, you architect, build, and operationalize cutting-edge Generative AI and LLM solutions to transform Citi’s operational teams. You work with cross-functional partners to deliver enterprise-grade AI capabilities at scale, balancing research with production software engineering. You will design end-to-end GenAI pipelines, ensure governance and compliance, and mentor junior developers, shaping AI solutions across the COO Technology division. Compensation / Benefits * Design and implement end-to-end Generative AI pipelines, including LLM integrations, RAG systems, autonomous agents, and prompt frameworks * Develop robust Python services and APIs powering AI-driven features across COO platforms * Evaluate and fine-tune LLMs and embeddings for financial use cases (GPT-5, Claude, Mistral) * Build ML/GenAI deployment pipelines with MLOps for reliability, observability, and governance * Design multi-agent orchestration frameworks for complex operational workflows * Collaborate with AI Risk and Compliance to meet regulatory and data privacy standards * Design data pipelines and optimize vector databases (Pinecone, Weaviate, pgvector) for AI systems * Mentor junior developers, lead code reviews, contribute to GenAI standards across COO Technology * Translate COO business requirements into technical AI solutions with clear trade-offs and timelines Tasks * 6+ years of software engineering experience * 2+ years focused on Generative AI / LLM development * Expert-level Python with async, API development (FastAPI, Flask) * Hands-on experience with GenAI & LLM stacks (LangChain, LangGraph, LlamaIndex) * Experience with Google Cloud AI Platform * Proven RAG architectures, embedding pipelines, vector search * Strong prompt engineering, few-shot, and chain-of-thought techniques * Experience integrating with LLM APIs (OpenAI, Azure OpenAI, Anthropic, AWS Bedrock, Google Vertex AI) * ML fundamentals with fine-tuning (LoRA, PEFT) and inference optimization * Cloud experience with AWS, Azure, or GCP; data engineering with SQL, NoSQL, vector DBs (Pinecone, Weaviate, Chroma, pgvector) * CI/CD, Docker, Kubernetes, Git, automated testing * Financial services acumen (preferred) Key requirements * medical, dental & vision coverage * 401(k) * life, accident, and disability insurance * wellness programs * paid time off * vacation and holidays

Requirements

Platform * Collaborate with AI Risk and Compliance to meet regulatory and data privacy standards * Design data pipelines and optimize vector databases (Pinecone, Weaviate, pgvector) for AI systems * Mentor junior developers, lead code reviews, contribute to GenAI standards across COO Technology * Translate COO business requirements into technical AI solutions with clear trade-offs and timelines Tasks * 6+ years of software engineering experience * 2+ years focused on Generative AI / LLM development * Expert-level Python with async, API development (FastAPI, Flask) * Hands-on experience with GenAI & LLM stacks (LangChain, LangGraph, LlamaIndex) * Experience with Google Cloud AI Platform * Proven RAG architectures, embedding pipelines, vector search * Strong prompt engineering, few-shot, and chain-of-thought techniques * Experience integrating with LLM APIs (OpenAI, Azure OpenAI, Anthropic, AWS Bedrock, Google Vertex AI) * ML fundamentals with fine-tuning (LoRA, PEFT) and inference aaaa features * Cloud experience with AWS, Azure, or GCP; data engineering with SQL, NoSQL, vector DBs (Pinecone, Weaviate, Chroma, pgvector) * CI/CD, Docker, Kubernetes, Git, automated testing * Financial services acumen (preferred) Key requirements * medical, dental & vision coverage * 401(k) * life, accident, and disability insurance * wellness programs * paid time off * vacation and holidays

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on us.experteer.com

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

40 sec

Generative pre-trained transformer models powering code completions

lgonta lgonta +1 · WWC 2024

6:21 min

Investigating push inefficiencies with upstream Git experts

Jonathan Creamer · Coffee With Developers

2:37 min

Comparing traditional SQL tables versus NoSQL non-tabular databases

Stanimira Vlaeva · JS Congress

52 sec

Transitioning from software consulting to AI building

Malte Lensch Malte Lensch · WWC Europe 2026

51 sec

Assessing GPT-4o performance for pull request feedback

Merrill Lutsky Merrill Lutsky · WWC 2025

2:08 min

Essential engineering roles in the generative AI space

Mary Grygleski Mary Grygleski · LIVE

Videos

See all

Related articles

See all