Staff Software Engineer, AI

<h2><strong>This is Engineering at Lattice</strong></h2> <p>At Lattice, we build software that helps people and organizations thrive. Our AI Engineering team defines how intelligence works across our platform - how AI systems are measured, improved, and trusted in production.</p> <p>This Staff-level role shapes the foundations that determine AI quality, reliability, and impact at scale.</p> <h2><strong>What You Will Do</strong></h2> <p>You will architect and scale the infrastructure that powers AI quality, reliability, and reuse across Lattice.</p> <h3>AI Evaluation &amp; Quality</h3> <ul> <li>Design and scale an end-to-end AI evaluation framework spanning offline evals, production tracing, and human feedback loops.</li> <li>Define meaningful performance metrics (task completion, hallucination, response quality, engagement, business impact) and build the datasets and automated scoring systems that prevent regressions.</li> <li>Identify and quantify the drivers of agent quality improvement and set methodological standards for evaluation across the organization.</li> </ul> <h3>Agent Architecture &amp; Production Systems</h3> <ul> <li>Architect reusable agent infrastructure (multi-turn workflows, LLM DAGs, recommendation systems, standardized topologies) using LangGraph or comparable frameworks.</li> <li>Build and scale RAG pipelines, vector retrieval systems, and production-grade AI infrastructure with strong reliability, observability, and performance.</li> <li>Make principled build-vs-buy decisions across LLM providers, agent frameworks, and evaluation tooling, balancing capability, cost, latency, and risk.</li> <li>Engineer AI systems as reusable internal platforms that multiply product engineering velocity at Lattice.</li> </ul> <h3>Technical Leadership</h3> <ul> <li>Own projects end-to-end: scope, design, execution, and delivery.</li> <li>Set technical direction for agent quality and evaluation strategy across Lattice engineering teams.</li> <li>Lead rigorous discussions on AI system design and evaluation methodology.</li> <li>Raise the AI engineering bar through mentorship, code review, and clear technical communication across engineering and leadership.</li> </ul> <h2><strong>What You Will Bring to the Table</strong></h2> <h3>Experience</h3> <ul> <li>8+ years of professional experience writing and maintaining production-level code, with 5+ years in designing, delivering, and operating AI/ML systems in production.</li> <li>Deep production experience with LLM systems (prompting, RAG, agent orchestration, evaluation frameworks, fine-tuning).</li> <li>Experience building and operating