Speakers1 - 10 of 15
Open a speaker to read their bio and see everything they're presenting.
Sessions (1)
- Evaluation harnesses for production LLMs
Monday, October 12: 10:00 AM - 10:45 AM · Workshop Room
AI Engineering
- Evaluation harnesses for production LLMs
Authoritative bio, edited in my own portal.
Sessions (2)
- Edited In Airtable — two-way proof 15:30:57
Date and time to be announced
AI Engineering - Edited In Airtable — two-way proof 15:35:19
Date and time to be announced
AI Engineering
- Edited In Airtable — two-way proof 15:30:57
An updated bio from the verify script.
Sessions (1)
- Verification Talk (edited)
Monday, October 12: 05:00 AM - 05:45 AM · Main Stage
AI Engineering
- Verification Talk (edited)
Yara works on the developer platform at Cirrus Payments and maintains two widely used open-source schema libraries.
Sessions (1)
- Structured output without the sadness
Monday, October 12: 02:00 AM - 02:45 AM · Main Stage
AI Engineering
- Structured output without the sadness
Hana works on calibration and abstention — teaching models to recognise the edge of their own competence. She publishes regularly and reviews for three conferences.
Sessions (1)
- Evaluation harnesses for production LLMs
Monday, October 12: 10:00 AM - 10:45 AM · Workshop Room
AI Engineering
- Evaluation harnesses for production LLMs
Sofia was the first engineer at Vantage Labs and now leads their agent runtime. She is unreasonably interested in what happens when a tool call fails halfway through.
Sessions (1)
- Building reliable agents: a practitioner's playbook
Monday, October 12: 10:00 AM - 11:00 AM · Main Stage
AI Engineering
- Building reliable agents: a practitioner's playbook
Sessions (1)
- Edited In Airtable — two-way proof 15:35:19
Date and time to be announced
AI Engineering
- Edited In Airtable — two-way proof 15:35:19
Sessions (1)
- Edited In Airtable — two-way proof 15:30:57
Date and time to be announced
AI Engineering
- Edited In Airtable — two-way proof 15:30:57
Ava leads the evaluation platform at Lumen AI, where she is responsible for making sure model changes ship without quietly regressing customer-facing quality. She spent six years in search relevance before moving to LLM systems.
Sessions (2)
- Building reliable agents: a practitioner's playbook
Monday, October 12: 10:00 AM - 11:00 AM · Main Stage
AI Engineering - Closing panel: what we got wrong about agents
Tuesday, October 13: 04:00 PM - 05:00 PM · Main Stage
Product
- Building reliable agents: a practitioner's playbook
Rewritten in the grid at 15:30:57.
Sessions (1)
- Opening keynote: the year AI engineering grew up
Monday, October 12: 09:00 AM - 09:45 AM · Main Stage
AI Engineering
- Opening keynote: the year AI engineering grew up