Staff Software Engineer, Applied AI Systems

We’re hiring a hands-on Staff Software Engineer to lead development in a critical area of AI-enabled product infrastructure. In this role, you will build and evolve the systems that determine what AI-powered experiences can access, use, and reference in real time. This work is central to ensuring outputs are accurate, timely, secure, and grounded in the right information.

You will focus on designing and improving retrieval and context systems that support intelligent applications operating in complex, high-trust environments. That includes helping systems identify the right content, manage changing information, and enforce strict access boundaries. You’ll work primarily in Python and collaborate closely with cross-functional partners in product, data, and engineering. This is a highly hands-on role for someone who wants to directly influence the architecture, quality, and safety of AI-driven capabilities.

What You’ll Do

• Lead the design and improvement of retrieval systems that support AI-powered workflows in production environments
• Ensure application outputs are grounded in the right source material, with the appropriate balance of quality, performance, and cost
• Build systems that can process and reason over large volumes of unstructured and structured content
• Develop search and context tools that surface trustworthy source excerpts, references, and relevant content locations
• Maintain alignment between what AI systems can access and what end users are authorized to view
• Help define when AI-generated outputs can be delivered directly and when additional validation or product controls are required
• Influence technical direction across teams and mentor engineers working in adjacent problem spaces
• 6+ years of experience building and operating production software, including leading technically complex initiatives across teams
• Strong hands-on Python experience, especially in backend systems, APIs, and data-intensive services
• Experience with production AI or machine learning applications that rely on retrieval, search, context assembly, or tool orchestration
• Strong understanding of access controls, permissions, and secure handling of multi-tenant or sensitive data
• Sound product and engineering judgment, with the ability to make tradeoffs across quality, latency, and cost and communicate those decisions clearly

Nice to Have

• Experience with long-running AI workflows or systems that interact with large document sets
• Experience operating vector-based or semantic search infrastructure in production
• Familiarity with large-document processing, structured data extraction, or search relevance evaluation
• Experience building systems that generate citations, evidence trails, or traceable outputs
• Background in document-heavy or compliance-sensitive software environments
• Experience designing tool interfaces for AI-enabled systems