Applied AI Engineer
Our client is seeking an Applied AI Engineer with 10+ years of experience to design, build, and operationalize generative AI solutions across their Lending business lines. This role offers the opportunity to architect enterprise-grade GenAI workflows, establish LLMOps best practices, and evolve into a platform owner for shared AI standards.
Responsibilities & Qualifications
Design and evolve reusable GenAI workflows and agentic systems deployed across multiple Lending business units
Develop enterprise-grade AI-powered document ingestion, data extraction, and content generation capabilities
Build AI assistants embedded in Lending systems using agentic workflows and orchestration patterns
Deliver automated workflows for content generation, reporting, and approval processes
Establish and operationalize LLMOps practices including extraction accuracy monitoring, prompt management, and audit controls
Design and implement security controls for entitlements, PII handling, and governance within AI systems
Provide expert technical guidance on GenAI architecture, model selection, and platform orchestration decisions
Act as hands-on technical expert with a clear advancement path to platform owner for enterprise GenAI standards
Requirements
10+ years of software engineering experience with demonstrated expertise in generative AI solutions
Strong proficiency with LangChain, LLM platforms, and RAG (Retrieval-Augmented Generation) architectures
Production-level experience with Python or Java and building scalable ML systems
Hands-on expertise in agentic workflows, vector search, prompt management, and data ingestion pipelines
Deep understanding of LLMOps practices including model monitoring, logging, and production reliability
Experience designing and implementing data pipelines and working with large language models in enterprise environments
Strong grasp of AI security, compliance, and governance requirements for financial services or similarly regulated industries