automation
Agentic pipelines and workflow orchestration: LLM-powered systems that run unattended and know when to stop. Human-in-the-loop design places people exactly where judgment matters, and nowhere else.
independent practice · automation · optimization · modeling · ai
matrices.
systems that decide, adapt, and improve themselves.
the practice of sam cialek
book a consultation →
the practice
01–04
matrices works where four disciplines overlap: systems that make decisions, measure their own performance, and get better with every pass.
optimization
Portfolio and resource-allocation optimization, and decision analysis under uncertainty. Objectives built on the full distribution of outcomes, not just the expected value, because the tails are where plans break.
modeling
Bayesian inference in Stan, PyMC, and NumPyro. Causal DAGs and treatment-effect estimation, agent-based simulation with synthetic populations, and probabilistic forecasting that states its uncertainty plainly.
ai
Applied LLM systems with evaluation and scoring pipelines built in from the start. Adaptive question engines, and machine learning that ships.
selected work
3 projects
serif
consumer health
A consumer-health causal inference engine. Turns wearable and biomarker data into personalized, dose-aware recommendations through a causal DAG and Bayesian posteriors, built across 3 cohorts.
prism
political disposition
A Bayesian adaptive quiz over 14 latent dimensions. Questions adapt in real time to what each answer reveals, and the engine converges on a result in about 30 questions.
markets
prediction markets
Prediction-market tooling: Bayesian decomposition of contract prices into shared latent terms, live dashboards, and an active forecasting track record.
about
est. nyc
sam cialek
Fifteen years across quantitative finance, data science, and software engineering. The constant throughout: decisions under uncertainty, treated carefully enough to build systems around them.
M.S. Computer Science
georgia tech, 2024
MBA
columbia business school, 2019
B.A. Economics & Mathematics
nyu, 2011
contact
sam@matrices.earth
start a conversation.
A short call is the fastest way to find out whether a problem is a fit for the practice.