About the role

Enterprise AI Platform Architect at Acquia building and deploying AI workflows in production environments. Leading end-to-end AI agent implementations and optimizing platform scalability and performance.

Responsibilities

Lead end-to-end delivery of AI agent implementations
Conduct architectural reviews and provide recommendations for optimizing AI platform performance, scalability, and security
Lead the design and deployment of production-grade AI systems as an active contributor writing high-impact code. Expect to live in Python, LangGraph, and LangFuse to turn vision into reality.
Architect sophisticated, stateful, multi-agent workflows using LangGraph. You will build the frameworks that allow autonomous agents to operate with enterprise-level reliability and scale.
Champion AI observability by integrating LangFuse for deep tracing, prompt versioning, and rigorous evaluation. You’ll turn "black box" LLM interactions into transparent, benchmarked performance data.
Define the engineering blueprints for the entire organization. You will establish patterns for RAG architecture, advanced tool-calling, context window optimization, and prompt engineering.
As the internal scout for emerging tech, you will benchmark new LLM providers and orchestration frameworks, ensuring our stack remains at the cutting edge of the agentic revolution.

Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, or a related field
7+ years of experience in cloud computing architecture, software engineering, or technical consulting
3+ years of experience in AI/ML platform architecture and development, with deep recent experience (2+ years) in generative AI and agentic architectures in production applications.
Demonstrated track record of shipping AI applications to production environments, not just prototypes.
Hands-on LangGraph — stateful, cyclic, multi-agent workflows at enterprise scale.
Hands-on LangFuse - tracing, evaluation, prompt management, and dataset-driven testing
Python proficiency and strong engineering fundamentals (testing, CI/CD, architecture).
Cloud AI deployment experience (AWS, Azure, or GCP) including containerization and inference cost management.
RAG architecture knowledge— vector databases, embedding models, and retrieval strategies.