All speakers

Willem Pienaar

Co-Founder & CTO, Cleric

Willem is the Co-Founder and CTO of Cleric, an AI Site Reliability Engineer that autonomously investigates and resolves production issues. He also created the Feast Feature Store, an open source project widely adopted for ML feature management. Prior to Cleric, Willem was a Principal Engineer at Tecton and led the ML Platform at Gojek.

Willem Pienaar

Sessions / 2025 / 1 talk

  • Chaos By Design: Simulation Based Testing for AI Agents

    Not all AI agent use cases are created equal. While code generation agents can be tested against clear benchmarks, operational agents tackling real-world problems face a fundamentally different challenge: how do you evaluate an agent that must navigate complex, dynamic systems without a predefined playbook? Take root cause analysis in distributed systems: an agent must understand intricate service dependencies, parse through inconsistent logs, and reason about potential failure modes. Unlike coding tasks with definitive right answers, these scenarios have no ground truth. Traditional testing approaches break down completely. This talk breaks down our approach to building a deterministic simulation environment that generates and tests realistic failure scenarios at scale. We'll expose why existing evaluation methods fail—from infrastructure mimicry to LLM-generated tests—and demonstrate a lightweight simulation technique that enables precise, reproducible agent testing.

Sessions / 2018 / 1 talk

  • Building a Feature Platform to Scale Machine Learning

    Go-Jek, Indonesia’s first billion-dollar startup, has seen an incredible amount of growth in both users and data over the past two years. Many of the ride-hailing company's services are backed by machine learning models. Models range from driver allocation, to dynamic surge pricing, to food recommendation, and process millions of bookings every day, leading to substantial increases in revenue and customer retention. Building a feature platform has allowed Go-Jek to rapidly iterate and launch machine learning models into production. The platform allows for the creation, storage, access, and discovery of features by both data scientists and models in production. It supports both low latency and high throughput access in serving, as well as high volume queries of historic feature data during training. The platform has dramatically decreased the time to market for their ML systems, while simultaneously increasing predictive accuracy. Find out more about the challenges Go-Jek faced while building the feature platform, the lessons they learned, and how they ultimately delivered a system that would allow them to scale ML.

Ready to take this stage?

The next edition is programmed by practitioners. Tell us what you built and what you learned.

Apply to be a speaker