Staff AI Engineer (Acquia DAM)

Acquia is the digital experience platform built for a world where your audience isn't only human, its agents too. As a Staff AI Engineer within R&D, you will drive the technical evolution of Acquia DAM, a market-leading platform that transforms how global brands manage content using AI features including auto-tagging, automated facial recognition, duplicate asset detection, and natural language search. You will integrate DAM deeply with the broader Acquia AI ecosystem, architecting roadmap themes centered on autonomous asset governance, agentic orchestration, and smart visual transformations.

Responsibilities

• Write and ship production AI code daily, you are an active contributor, not an advisor.
• Architect agentic AI workflows using LangGraph, Temporal, and Pydantic: stateful, multi-agent workflows built for enterprise scale and reliability.
• Own AI observability via LangFuse: tracing, prompt versioning, evaluation, and performance benchmarking across all model interactions.
• Set AI engineering standards for agent design patterns, RAG, prompt management, context optimization, and tool-calling strategies.
• Partner with product and platform teams to deliver AI architectures that meet enterprise SLA, security, and compliance requirements.
• Evaluate and adopt emerging tooling, benchmarking LLM providers, orchestration frameworks, and agentic stack improvements.
• Mentor engineers through code reviews, pairing sessions, and design discussions, and represent Acquia's AI capabilities in customer architectural reviews and roadmap conversations.

Qualifications

• 8+ years of software engineering with 3+ years building production AI agents.
• Hands-on LangGraph, Temporal, and Pydantic expertise with stateful, cyclic, multi-agent workflows at enterprise scale.
• Hands-on LangFuse expertise: tracing, evaluation, prompt management, and dataset-driven testing.
• Proficiency with agent harness frameworks such as LangChain or similar (LlamaIndex, CrewAI), composing chains, tools, memory, and retrieval pipelines.
• Deep 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.
• B.S. in Computer Science or equivalent practical experience.
• Desired: enterprise SaaS or CMS experience, AI-assisted coding fluency, persistent agent runtimes, LLM fine-tuning or model evaluation, human-in-the-loop agent design, and a senior IC track record.