Senior AI Engineer - Brown Brothers Harriman

At BBH, Partnership is more than a form of ownership—it’s our approach to business and relationships. We know that supporting your professional and personal goals is the best way to help our clients and advance our business. We take that responsibility seriously. With a 200-year legacy and a shared passion for what’s next, this is the right place to build a fulfilling career.

About the Role

As an AI Engineer, you'll build the intelligence layer of the platform - the AI-powered features that allow financial services users to generate data transformations from natural language, get intelligent integration suggestions, detect data quality issues, and refine outputs based on feedback. This is where the product stops feeling like a tool and starts feeling genuinely new.

This is a hands-on production role. You'll build and iterate on LLM pipelines, RAG systems, and agentic workflows using Agno; optimize AI systems for accuracy, latency, and cost in a context where correctness matters; and collaborate closely with Backend Engineers to ensure AI capabilities are reliably surfaced through the platform. You'll work under the direction of the Head of AI Engineering and have real ownership over the features you build.

Responsibilities

AI Feature Development

• Build and iterate on AI-powered product features - transformation generation from natural language, integration configuration suggestions, data quality detection, and automated validation
• Implement LLM pipelines that are robust, observable, and production-ready - not proof-of-concepts

LLM Pipeline Engineering

• Build and optimize LLM pipelines including prompt engineering, context management, and RAG systems tailored to financial services data schemas
• Evaluate and improve AI output quality continuously - build evaluation datasets and automated scoring frameworks
• Optimize for accuracy, latency, and cost across different usage patterns

Agentic Workflows

• Implement multi-step agentic workflows using Agno,
• Build workflows that handle complex, multi-turn AI interactions cleanly - with proper error handling, retry logic, and human escalation paths

Platform Collaboration

• Work closely with Backend Engineers to integrate AI capabilities into the platform's API and workflow layer
• Build the service interfaces that connect AI outputs to platform execution cleanly
• Participate in code reviews and maintain high standards for code quality and testability

Requirements

Experience

• 5+ years software engineering; 1+ years focused on GenAI/LLM applications in production
• Has shipped AI features to real users - not just prototypes or internal demos

Technical Skills

• Hands-on with LLM APIs in production - Anthropic Claude and/or OpenAI