Senior GenAI Engineer, Production LLM Pipelines

Brown Brothers Harriman; Boston (MA); On-site; USD 175,000 - 215,000; Full time

Job summary

BBH in Boston seeks an AI Engineer to build the AI-powered features of our platform, enabling natural language-driven data transformations, intelligent integration suggestions, and data quality tooling. You will own LLM pipelines, RAG systems, and agentic workflows, collaborating with Backend Engineers to surface capabilities through the API.

You will report to the Head of AI Engineering and deliver production-ready AI features with a focus on accuracy, latency, and cost in a financial services

Qualifications

• 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

Responsibilities

• Build and iterate on AI-powered product features: transformations from natural language, config suggestions, data quality detection, automated validation.
• Implement robust LLM pipelines that are observable and production-ready, including prompt engineering, context management, and RAG systems.
• Create multi-step agentic workflows using Agno and ensure error handling, retries, and proper escalation.
• Collaborate with Backend Engineers to integrate AI capabilities into the platform's API and workflow layer; build service interfaces connecting outputs to platform execution; participate in code reviews and maintain high standards.

Skills

Python

LLM APIs

RAG systems

Agno/agentic

LangChain

Cloud: Azure/AWS

Vector databases

Code quality/testing

Data transformation

Tools

Agno

LangChain

LlamaIndex

Pinecone

Weaviate

pgvector

Job description

BBH in Boston seeks an AI Engineer to build the AI-powered features of our platform, enabling natural language-driven data transformations, intelligent integration suggestions, and data quality tooling. You will own LLM pipelines, RAG systems, and agentic workflows, collaborating with Backend Engineers to surface capabilities through the API.

You will report to the Head of AI Engineering and deliver production-ready AI features with a focus on accuracy, latency, and cost in a financial services