Machine Learning & AI Systems
Building and deploying ML systems that work in production.
Large Language ModelsGenerative AINLP & Voice InterfacesDeep LearningReinforcement LearningForecasting & Predictive ModelingMLOps & Model Serving
Michael Ellis
Hello! I'm Michael, a data scientist with a math and statistics background who likes to build things. My work spans Bayesian methods and causal inference to LLMs, GenAI, and AI agents. I believe good data science requires good software engineering. Currently, I'm especially interested in the intersection of causal inference and agentic AI, building systems that use causal reasoning for counterfactual simulation and intervention planning.
Areas of Expertise
Specialized skills and technologies I bring to every project
Statistical Inference & Experimentation
Building production-grade systems with clean architecture, rigorous DevOps, and scalable infrastructure.
Bayesian InferenceCausal InferenceA/B Testing & ExperimentationTime Series and Spatial DatasetsMonte Carlo MethodsHigh-Dimensional Probability & Statistics
Software Engineering
Building production-grade systems with clean architecture and rigorous DevOps practices.
PythonC++TypeScript & JavaScriptNext.js & ReactNode.jsSystem Design & ArchitectureCI/CD & DevOpsCloud Infrastructure (GCP)
Open Source
Select projects from my GitHub - statistical computing, ML, and developer tooling
smcjax
Sequential Monte Carlo and particle filtering in JAX
Pythonbayesian-inferencehidden-markov-modelsjaxparticle-filterpythonsequential-monte-carlostate-space-models
lmxlab
Language model research platform for Apple Silicon — 24 architectures, MLX-native training, LoRA/DPO/GRPO, and experiment tracking
Pythonapple-silicondeep-learninglanguage-modelsllmloramachine-learningmambamixture-of-expertsmlxpythonrlhftransformer
pypkgkit
Production-ready Python package template with uv, ruff, pyright, and GitHub Actions CI/CD
Pythonci-cdgithub-actionspyrightpythonrufftemplateuv
VBMM
Bayesian Gaussian mixture models with Gibbs sampling and variational inference in R
Rbayesian-inferencegaussian-mixture-modelsgibbs-samplermixture-modelsrvariational-inference
dirichlet-process-mixtures
Bayesian inference for Dirichlet process mixture models using Gibbs sampling and variational approximations in R
Rbayesian-inferencedirichlet-processgibbs-samplermixture-modelsnonparametric-statisticsrvariational-inference
variational-inference
Variational Bayes and CAVI algorithms from Ormerod & Wand — approximate Bayesian inference examples in R
Rapproximate-inferencebayesian-inferencemachine-learningrstatisticsvariational-inference
gaussian-process
Full Bayesian inference for Gaussian process spatial models using MCMC in R
Rbayesian-inferencegaussian-processesgeostatisticsmcmcrspatial-statistics
My Journey
Professional experience and academic achievements
Loading timeline...