Staff AI Engineer

This is a heavy-hitting Staff AI Engineer role for someone who wants to lead architecture while keeping their hands dirty with code. You will be building production-grade LLM systems, agentic workflows, and RAG pipelines for both internal and customer-facing enterprise initiatives.

What You'll Actually Be Doing

Your typical week will be split between deep architectural planning and high-impact coding. You'll take ambiguous, poorly defined enterprise problems and map them out from discovery to deployment, dealing with real-world issues like latency, cost optimization, and failure handling. You won't just be shipping code; you'll be mentoring other engineers, defining reusable patterns, and establishing production standards for AI evaluation and observability across the entire team.

The Core Tech Stack

You need a rock-solid foundation in Python and full-stack development, alongside deep, hands-on experience with LLMs, embeddings, RAG, and agentic workflows. They use PostgreSQL, React, and C# in their environment, but your ability to architect scalable AI systems that actually survive production is way more important than checking every single syntax box.

Interview Expectations

Expect to be grilled on your past production AI deployments, specifically around how you handled cost, latency, and hallucination guardrails in real applications. The hiring manager is going to throw a vague system design scenario at you—such as building a multi-agent retrieval system with strict SLAs—and they want to see how you weigh architectural tradeoffs, model selection, and fallback strategies.

Application Advice

To make your resume stick out to the ATS, make sure you explicitly separate your production AI deployments from simple API wrappers or proofs-of-concept. Use keywords like 'RAG', 'agentic workflows', 'production AI evaluation', and 'system architecture' right at the top of your experience bullets, and highlight any instances where you mentored engineers or drove technical direction from 0 to 1.