Senior Generative AI Engineer — LLM, RAG, & AI Governance

Citigroup Inc.

Irving (TX)

Hybrid

USD 156,000 - 234,000

Full time

3 days ago

Be an early applicant

Get more replies from employers

Send a job-specific resume in minutes.

Benefits offered by this job

Hybrid work model

Competitive compensation and benefits

Job summary

Citi in Irving, Texas seeks a Principal Generative AI Engineer to lead design, development, and deployment of intelligent operations and automation platforms within the AI Automation Forward Deployed Engineering team. You will set the technical direction for generative AI solutions, from LLM orchestration to AI governance, ensuring security, compliance, and reliability in financial services.

This senior role offers global collaboration, hybrid work flexibility, and strategic ownership on

Qualifications

10 or more years of experience in application development or engineering, with a significant focus on AI and machine learning solutions in production environments.
Deep expertise in LLM architectures, embedding models, and AI orchestration frameworks such as Google ADK and LangChain, applied to real-world operational use cases.
Hands-on experience deploying open-source LLMs (Llama, Mistral, Gemma) and working with enterprise AI platforms including Google Vertex AI or equivalent cloud AI suites.
Expert-level Python skills, including proficiency with AI/ML libraries such as PyTorch, Hugging Face, Pandas, and NumPy, and API development frameworks including FastAPI and Flask.
Demonstrated ability to implement deterministic controls, bias detection, and hallucination mitigation in production AI systems operating under strict compliance requirements.
Strong experience with containerisation technologies (OpenShift, Docker, Kubernetes) and cloud-native application delivery, including CI/CD pipeline management.
Background in financial services technology, with working knowledge of financial products, compliance requirements, and data security standards in a regulated environment.

Responsibilities

Architect and deliver end-to-end generative AI solutions for intelligent operations, including advanced chatbots, agentic workflow automation, and AI-assisted decision platforms that improve operational efficiency at scale.
Lead the engineering of LLM pipelines by fine-tuning, prompt-engineering, and deploying open-source models such as Llama, Mistral, and Gemma alongside proprietary models via Google Vertex AI.
Build and maintain Retrieval-Augmented Generation (RAG) pipelines using vector databases such as Pinecone, Milvus, and Chroma to enhance model accuracy and contextual relevance.
Design and implement AI governance frameworks, including guardrails (NeMo Guardrails, Llama Guard), deterministic controls, semantic routing, and hallucination detection systems to ensure safe and compliant production AI.
Deploy scalable, cloud-native AI infrastructure using Python, Docker, Kubernetes, and OpenShift, supported by robust CI/CD pipelines for continuous delivery.
Apply deep knowledge of financial services technology to ensure all AI models meet strict risk management, auditability, and data security standards aligned with regulatory requirements.
Partner with senior technology leaders and cross-functional teams to translate complex business challenges into production-ready AI solutions, setting credible technical direction throughout delivery.