Fabio Flores
He / him / his
Software Engineer, Agents @DoorDash
Fabio Flores is a tech lead on DoorDash’s Agentic Ordering team, where he sets the technical direction for model and evaluation foundations. His work spans model selection, post-training, inference optimization, and the evaluation systems that guide their development and rollout. He connects production feedback with offline experimentation to shape model strategy and agent architecture, improving agent capabilities while managing the tradeoffs between quality, latency, and cost.
From Signal To Impact: The Eval Loop Behind Doordash’s Agentic Ordering System
Running an LLM judge is the easy part of agent evaluation. The harder problem is building a system whose results are repeatable, diagnostic, and actionable. Production agents operate across multi-turn conversations, tool calls, specialized agents, and changing external state.
Video is not available
Slides are not
available
