AI Engineer Summit 2026

Hana works on calibration and abstention — teaching models to recognise the edge of their own competence. She publishes regularly and reviews for three conferences.

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.

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.

Priya runs the platform organisation at Cobalt Systems, covering everything from developer experience to the inference fleet. She has been a programme chair three times and still enjoys it.