Sr Principal AI Architect

About the role

Sr Principal AI Architect position based in the Bay Area, CA. Relocation considered. Full-time.

Responsibilities

• Work on the intelligence layer for multiple programs, owning model quality, RAG accuracy, prompt engineering, and AI safety across applications.
• Develop Socratic tutor persona, adaptive learning recommendation engine, multi‑modal AI (text and voice), RAG evaluation framework, and feedback loop into retrieval.
• Orchestrate multi‑step LLM call chains (NeMoGuardrails intent classification, query rewriting, RAG synthesis) and implement compatibility check logic.
• Ensure production‑grade AI quality from launch: define accuracy thresholds, latency requirements, and safety guardrails that must pass InfoSec adversarial testing before Release 1.

Requirements

• 15+ years total IT experience; 4‑7 years of software engineering; at least 2 years focused on LLM application development in production.
• Has shipped an LLM‑powered feature or product to production where real users depend on accuracy and the engineer owns the quality metrics.
• Has owned an AI safety or guardrails implementation for a customer‑facing product (designed and tested the safety layer, not just an off‑the‑shelf filter).
• Has built RAG evaluation pipelines and used them to make go/no‑go release decisions; accuracy gating is part of the workflow.
• Has profiled and optimized a multi‑step LLM call chain for latency.

Skills

• LLM prompt engineering: system prompts, few‑shot examples, chain‑of‑thought, instruction following.
• Multi‑step L