Lead AI Engineer - AI & Credit Analytics

Experian • Costa Mesa, CA

12h • Hybrid

About The Position

You will design scalable, production-grade agentic AI systems to automate and enhance credit analytics and credit decisioning workflows. You will integrate AI solutions across the credit lifecycle, including origination, underwriting, limit setting, portfolio monitoring, model validations and other use cases. Prototype, evaluate, and productionize GenAI solutions, translating new industry advancements into scalable enterprise applications. You will design and manage memory and state systems, including conversational memory and long-term knowledge storage (vector and structured data). You will design advanced RAG-based architectures including hybrid retrieval, query planning, re-ranking, and grounding validation applying both structured and unstructured enterprise data sources. Establish evaluation and guardrail frameworks, including hallucination detection, response validation, and human-in-the-loop controls including offline evaluation using ground truth datasets and controlled validation cycles. Build and deploy enterprise-grade GenAI services with focus on scalability, reliability, security, latency optimization and performance tuning in. Implement LLMOps / GenAIOps practices, including prompt versioning, model routing, monitoring, CI/CD pipelines and observability metrics (latency, cost, token usage, and response quality). You will collaborate with teams (analytics, engineering, product) to embed AI into existing solutions and develop new AI-driven offerings, being a bridge between platform engineering and AI application teams. Leverage and evaluate modern orchestration frameworks and cloud-native tools (e.g., LangGraph, AWS Bedrock, AWS Strands SDK or similar), while staying current with new paradigms such as MCP and A2A.

Requirements

• Master's degree in Computer Science, Data Science, or a related quantitative field
• 8–10 years of experience in data science, machine learning, or AI engineering, with experience building production-grade AI/ML or GenAI systems
• Domain experience in financial services
• Experience working in regulated environments, with understanding of data governance, model risk management, compliance, and responsible AI considerations
• Hands-on experience with Generative AI and LLM-based applications, including RAG architectures, prompt engineering, evaluation techniques, and system optimization in production-grade environments (not limited to prototyping)
• Proficiency in Python (required) and SQL, with an ability to build scalable pipelines, APIs, and production-ready AI solutions
• Familiarity with modern GenAI frameworks

Responsibilities

• Design scalable, production-grade agentic AI systems to automate and enhance credit analytics and credit decisioning workflows.
• Integrate AI solutions across the credit lifecycle, including origination, underwriting, limit setting, portfolio monitoring, model validations and other use cases.
• Prototype, evaluate, and productionize GenAI solutions, translating new industry advancements into scalable enterprise applications.
• Design and manage memory and state systems, including conversational memory and long-term knowledge storage (vector and structured data).
• Design advanced RAG-based architectures including hybrid retrieval, query planning, re-ranking, and grounding validation applying both structured and unstructured enterprise data sources.
• Establish evaluation and guardrail frameworks, including hallucination detection, response validation, and human-in-the-loop controls including offline evaluation using ground truth datasets and controlled validation cycles.
• Build and deploy enterprise-grade GenAI services with focus on scalability, reliability, security, latency optimization and performance tuning.
• Implement LLMOps / GenAIOps practices, including prompt versioning, model routing, monitoring, CI/CD pipelines and observability metrics (latency, cost, token usage, and response quality).
• Collaborate with teams (analytics, engineering, product) to embed AI into existing solutions and develop new AI-driven offerings, being a bridge between platform engineering and AI application teams.
• Leverage and evaluate modern orchestration frameworks and cloud-native tools (e.g., LangGraph, AWS Bedrock, AWS Strands SDK or similar), while staying current with new paradigms such as MCP and A2A.

Benefits

• Great compensation package and bonus plan
• Core benefits including medical, dental, vision, and matching 401K
• Flexible work environment, ability to work remote, hybrid or in-office
• Flexible time off including volunteer time off, vacation, sick and 12-paid holidays

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Number of Employees: 501-1,000 employees