We are seeking a skilled Chief GenAI Engineer to lead the design and implementation of advanced AI-powered workflows for automating mortgage document review, data extraction, and due diligence on a large scale.
This role offers the chance to work with innovative technologies like AWS Bedrock, LLMs, RAG, and serverless architectures, while collaborating with a multidisciplinary team to create impactful enterprise solutions.

REQUIREMENTS

• 7+ years of experience in Machine Learning Engineering
• Knowledge of AWS Bedrock components such as BDA, Blueprints, Knowledge Base, and Agents, including Prompt Engineering and Management
• Background with LLM architectures, RAG frameworks, and document chunking techniques for retrieval and extraction
• Proficiency in Python or Node.js for creating serverless pipelines
• Demonstrated experience delivering and maintaining high-throughput workflow solutions using Lambda Functions, Lambda Layers, Step Functions, SQS, EventBridge, Aurora RDS Serverless, and Amazon Textract
• Competency in deploying high-volume, high-velocity workflows in enterprise environments
• Understanding of cloud architecture patterns, security, performance optimization, and cost-efficient designs for serverless and distributed systems
• Strong ability to resolve issues during debugging and effectively manage production incidents
• Effective communication skills with the ability to collaborate in dynamic, remote, cross-functional teams
• Flexibility to manage tight deadlines and changing priorities while maintaining high-quality delivery

• Deliver solutions for automating mortgage document OCR, data extraction, and due diligence using AWS Bedrock and supporting cloud services
• Integrate and optimize GenAI/RAG systems with Bedrock Prompt Engineering, Blueprints, Knowledge Base, chunking strategies, and LLM customization
• Create scalable and reliable cloud pipelines using Python or Node.js, as well as tools like Lambda functions, Aurora RDS, Step Functions, EventBridge, and SQS
• Design systems to handle up to 2 million documents per hour with high reliability, robustness, and low latency
• Ensure efficient workflows and system health by implementing monitoring, error tracking, and metrics
• Partner with AI PODs, product owners, and technical leads to accelerate workflow onboarding and improve delivery speed without sacrificing quality
• Apply industry standards in code quality, infrastructure security, compliance, and data privacy for enterprise-ready solutions
• Incorporate approved AI tools, including GitHub Copilot and ChatGPT Sandbox, to enhance productivity and ensure secure code development