RILEY CHEN
Seattle, WA · riley.chen@email.com · (555) 010-1102 · linkedin.com/in/RileyChenAI

SUMMARY
AI engineer with 2+ years shipping production LLM features: RAG pipelines, tool-calling agents, and evaluation loops that PMs trust. Comfortable owning prompt design through monitoring — not just notebook demos.

SKILLS
Python · LLM APIs (OpenAI, Anthropic, Gemini) · LangChain / LlamaIndex · Vector databases (Pinecone, Weaviate, pgvector) · RAG architecture · Prompt engineering · Fine-tuning (LoRA, PEFT) · LLM evaluation frameworks

EXPERIENCE
AI Engineer · Northbeam Labs · 2023-Present
• Launched a RAG support agent over 40k docs; raised deflection rate from 18% to 34% while holding escalation quality.
• Designed LLM eval suite (faithfulness, latency, cost); blocked 3 unsafe prompt rolls before customer impact.
• Fine-tuned a classifier with LoRA for intent routing; cut misroutes by 29% vs. zero-shot baseline.

AI Platform Engineer (contract) · Brightline · 2022-2023
• Wired LangChain tools to internal APIs with guardrails; cut median response latency from 4.8s to 2.1s.

EDUCATION
MS Computer Science · Pacific University · 2022