Senior Generative AI Developer
Role details
Job location
Tech stack
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