Staff Engineer, Applied AI

What you'll do

• Identify and evaluate opportunities for automating business processes using AI, intelligent workflows, and agent-based systems.
• Architect, build, and deploy applied AI solutions for automation, document intelligence, and decision support.
• Design and implement AI agents and agentic workflows to orchestrate tools, APIs, and business logic at scale.
• Build scalable, resilient, and high-performance systems using knowledge graphs to enhance reasoning and context retrieval.
• Translate business needs into technical designs and co-create scalable AI solutions with product and engineering partners.
• Mentor engineers and scientists through coaching, pairing, and architectural guidance on LLMs and agentic workflows.
• Run rigorous experimentation and evaluation including hypothesis definition, measurement, and iterative improvement in production.
• Establish engineering best practices for reliability, interpretability, safety, governance, and monitoring of production AI systems.

What we're looking for

• 8 or more years of professional software engineering or applied machine learning experience.
• 2 or more years of experience working with Generative AI or LLM-based systems in production.
• Hands-on experience with Python and frameworks including LangChain, LangGraph, LangSmith, LlamaIndex, Hugging Face, and OpenAI or Anthropic APIs.
• Experience designing, building, and operating production AI systems including agentic workflows and intelligent automation.
• Strong understanding of agent architectures, workflow orchestration, retrieval-augmented generation, vector databases, and knowledge graph integration.
• Experience mentoring engineers in AI, LLM, and agent-based system design.
• Competency in distributed systems, service design, performance optimization, and reliability engineering.
• Experience building advanced Generative AI capabilities, working in regulated industries, or deploying AI in Java ecosystems (preferred).