Niels van Galen Last
Niels van Galen Last is a Staff ML Engineer and Head of AI Engineering, focused on building production-grade AI and ML systems at scale. He leads the architectural foundation of a shared AI platform serving 35+ organizations, operating across distributed and international environments, with a focus on evaluation-driven development, reproducibility, and long-term system reliability.
His work centers on turning experimental models into robust systems: building evaluation frameworks, standardizing LLM and RAG architectures, and designing infrastructure for reliable deployment across cloud and hybrid environments. He has led high-impact AI systems across domains including document AI, optimization, and large-scale ML platforms.
Niels studied Computational and Mathematical Engineering at Stanford University and has held technical leadership roles across startups, consulting, and enterprise environments.
Session
Current LLM workflows work surprisingly well until context becomes the bottleneck. Tasks like multi-file code changes, long-log debugging, or stateful tool use that many teams attempt to solve with prompt engineering or agents often succeed at small scale and then become brittle as the amount of context grows.
This talk introduces Recursive Language Models (RLMs), a different approach in which context is treated as data that can be programmatically explored, decomposed, and revisited - rather than input that must be consumed in a single prompt. This shifts long-context LLM systems from brittle prompt orchestration to programs that explicitly explore, track, and update context over time.
Using DSPy as a concrete Python implementation, I will demonstrate how this approach turns a failing long-context task into a tractable one, and what this shift means for designing LLM systems in practice.
Attendees will leave with a clear mental model for when standard prompting breaks, what RLMs change technically, and how to prototype this pattern in practice.