Evolutionary LLM Systems for Code Optimization

Hosted by Amir Feizpour and Dmytro Nikolaiev

70 students

In this video

What you'll learn

Literature review of LLMs for code optimization

Productive exploration of code optimization

Where LLMs can improve perfomance

Eg. edits, refactors, hypotheses

Evaluation as the engine: writing task-aligned metrics

Why this topic matters

Modern LLM coding workflows often stall at “prompt tweaking.” In this session, we’ll look at a more systematic approach: putting LLMs inside evolutionary feedback loops to iteratively mutate, evaluate, and select better code - with measurable improvements on a target task. We’ll break down the core ingredients behind AlphaEvolve-style systems and adjacent research.

You'll learn from

Amir Feizpour

Founder @ Aggregate Intellect

Amir Feizpour is the founder, CEO, and Chief Scientist at Aggregate Intellect building a generative business brain for service and science based companies. Amir has built and grown a global community of 5000+ AI practitioners and researchers gathered around topics in AI research, engineering, product development, and responsibility. Prior to this, Amir was an NLP Product Lead at Royal Bank of Canada. Amir held a research position at University of Oxford conducting experiments on quantum computing resulting in high profile publications and patents. Amir holds a PhD in Physics from University of Toronto. Amir also serves the AI ecosystem as an advisor at MaRS Discovery District, works with several startups as fractional chief AI officer, and engages with a wide range of community audiences (business executives to hands-on developers) through training and educational programs. Amir leads Aggregate Intellect’s R&D via several academic collaborations.

Dmytro Nikolaiev

Dmytro Nikolaiev is a Machine Learning Scientist at ChainML (Theoriq)

Dmytro Nikolaiev is a Machine Learning Scientist at ChainML (Theoriq), where he builds and scales agentic LLM systems - from orchestration to evaluation and production monitoring. He’s especially interested in evolutionary algorithms, automated improvement loops, and “systems that get better with feedback.” Dmytro likes bridging research ideas with practical implementations: turning papers into repeatable engineering patterns, robust evaluation harnesses, and measurable system upgrades.