Maxime Rivest
Profile
Core Contributor at DSPy.
Biography
Maxime builds tools and create content that make LLMs more accessible and powerful for everyone. He is a core contributor to DSPy and has built numerous open-source Python libraries to advance the ecosystem, including attachments, functai, ovllm, dspy-lm-auth, dspy-template-adapter, and mcp2py. Previously, he worked at Elsevier, building AI infrastructure and compound AI programs to cost effectively run on 100 million records weekly.
Conference Sessions
- 2026 07 01 maxime rivest the unreasonable effectiveness of separating the task from the model โ The Unreasonable Effectiveness of Separating the Task from the Model (2026-07-01, 9:40am-10:00am)
Evidence Graph
This evidence graph summarizes how this person appears across the conference source graph: scheduled sessions, linked videos, transcripts, and slide-derived evidence.
Linked Sessions
Media Signals
youtube-I2cbIws9j10โ 91,792 transcript words; 7 slide-derived text signals- Transcript signals for
youtube-I2cbIws9j10: code, model, back, system, well, first, today, even. - Slide-derived themes for
youtube-I2cbIws9j10: context, window, selects, response, facts, retry, coerce, rollback. - Evidence links for
youtube-I2cbIws9j10: youtube I2cbIws9j10, youtube I2cbIws9j10 transcript, youtube I2cbIws9j10 slides, youtube I2cbIws9j10 dense slides
Livestream Appearances
- The Unreasonable Effectiveness of Separating the Task from the Model โ watch at 00:53:36 in WF26: Harness Engineering & Startup Battlefield (Day 3).