Senior AI Engineer - Production Agentic ML & RAG Systems

Blue Orange Digital; New York (NY); Remote; USD 180,000 - 230,000; Full time

Benefits offered by this job

Competitive compensation

Remote work flexibility

Professional development budget

Certification support

Collaborative team

Job summary

Blue Orange Digital is seeking a Senior AI Engineer to deliver production-grade agentic AI systems for client engagements. You will own the ML implementation workstream within an AI delivery pod, collaborating with an Architect and a Transformation Consultant to ship robust, scalable solutions.

Work spans deep, single-client transformations and portfolio programs across fintech, legal, and risk domains. You will design RAG pipelines, integrate tool-calling layers, and coach client teams in

Qualifications

• 5+ years building production data and ML systems in Python.
• 2+ years on LLM-based or agentic systems.
• Hands-on with at least one major LLM orchestration framework (e.g., LangChain, LangGraph, Langflow, Databricks Agent Framework).

Responsibilities

• Build production-grade agentic systems on Databricks and lakehouse platforms.
• Implement RAG pipelines and vector stores for scale.
• Stand up evals, observability, and guardrails for client AI systems.
• Design MCP servers and tool-calling layers between LLMs and client systems.
• Lead the AI engineering workstream on your pod with Architects and Consultants.
• Coach client teams on production AI patterns and FinOps.

Skills

Python

LLM orchestration

Production systems

Client coaching

Observability

FinOps

Tools

Databricks

LangChain/LangGraph

dbt

MLflow

Snowflake

Azure/AWS/GCP

Job description

Blue Orange Digital is seeking a Senior AI Engineer to deliver production-grade agentic AI systems for client engagements. You will own the ML implementation workstream within an AI delivery pod, collaborating with an Architect and a Transformation Consultant to ship robust, scalable solutions.

Work spans deep, single-client transformations and portfolio programs across fintech, legal, and risk domains. You will design RAG pipelines, integrate tool-calling layers, and coach client teams in