Beyond the Demo: Engineering AI That Actually Ships

Join Baseten and Rootly AI in Toronto for an evening with engineers working at the front lines of production AI.

Our panel will explore what happens between “the model works” and “the model is in production.” That includes how forward deployed engineering differs from traditional ML engineering, what it takes to build custom solutions for demanding customers, and how teams keep AI systems fast and reliable once real traffic hits.

Topics we’ll dig into:

• FDE vs. MLE: how the work, skills, and day-to-day actually differ

• Real examples of building new, cutting-edge solutions for specific customer needs

• Inference performance in practice, from speculative decoding to choosing the right optimizations for the job

• Using AI to keep production systems reliable when things break

Panelists

• Sylvain Kalache, Head of AI Labs, Rootly

• Daniel Buades Marcos, Engineering Manager, Forward Deployed Engineering, Baseten

• More speakers to be announced

Schedule
6:00–6:30 PM: Welcome drinks and snacks
6:30–7:30 PM: Panel and Q&A
7:30–8:00 PM: Wrap up and networking

📍 Rootly Toronto - 366 Adelaide St W, Unit 601
🗓 Thursday, November 19th