● ML engineer · data scientist
Hi, I'm Thamu. I'm a machine learning engineer focused on practical applied ML and AI systems that solve real business problems.
This site is where I publish my own thinking on applied AI, machine learning engineering, cloud-native data systems, and the practical lessons that come from building end-to-end solutions.
I also help organise my local Google Developer Group (GDG), which keeps me close to builders, students, engineers, and community conversations around emerging technology. Outside of work, I am learning German and preparing to write the A1 exam. The views here are my own. The goal is to share useful ideas, collaborate with people working on meaningful problems, and keep learning in public.
// 02 — Writing
How to evaluate RAG and agentic GenAI systems with MLflow 3.x, mlflow.genai.evaluate(), LLM-as-a-judge scorers, custom trace-aware metrics, and prompt A/B tests.
How MLflow 3.x helps productionise GenAI systems with OpenTelemetry-compatible traces, trace-aware evaluation, RAG judges, custom scorers, and prompt registry workflows.
A practical reflection on building Sentinel Health with spec-driven development, a PRD, AI-assisted programming, and a backend/frontend cloud MVP.
Wie man RAG- und agentische GenAI-Systeme mit MLflow 3.x, mlflow.genai.evaluate(), LLM-as-a-Judge-Scorern, eigenen trace-bewussten Metriken und Prompt-A/B-Tests bewertet.
Wie MLflow 3.x produktive GenAI-Systeme mit OpenTelemetry-kompatiblen Traces, trace-bewusster Evaluation, RAG-Judges, Custom Scorers und Prompt Registry Workflows unterstuetzt.
Comment evaluer les systemes RAG et agentiques avec MLflow 3.x, mlflow.genai.evaluate(), des scorers LLM-as-a-judge, des metriques trace-aware et des tests A/B de prompts.
Comment MLflow 3.x aide a industrialiser les systemes GenAI avec des traces compatibles OpenTelemetry, une evaluation consciente des traces, des juges RAG, des scorers personnalises et la Prompt Registry.
// 03 — What I do
Sitting at the intersection of business and AI, I try to focus on the solution first. The aim is to reach for the right tool for the job, whether that's generative AI, classical machine learning, or a straightforward heuristic. Most of the projects I'm part of run end-to-end, from helping frame the problem with stakeholders, designing and implementing the infrastructure, to monitoring, maintaining, and supporting new features once they're in production.
RAG systems and LLM agents where generative AI genuinely earns its place; classical ML, mathematical optimisation, or statistical methods where they do the real work underneath. In practice that has meant forecasting and demand modelling, operations optimisation, and retrieval-augmented assistants over internal data.
Training pipelines, model serving, drift monitoring, retraining, and governance work. I believe that the principles don't change with the stack, for example solid orchestration, automated testing, and observability that catches problems before users do.
Translate business outcomes into data and AI architectures. I sit between stakeholders and the model, framing the question before a single line of code is written.
Design reliable, cost-aware infrastructure for AI workloads, currently across Azure and Databricks and previously GCP. Terraform-certified, comfortable making infrastructure decisions.
// 04 — Background
// education
Thesis in the area of stochastics studying the stochastic area
Courses: Data mining, Time series, Extreme value theory, Multivariate Analysis, Simulation theory, Biostatistics
Courses: Statistics, Mathematics, Investment management, Economics, Accounting, Finance
// 05 — Certifications
Google Cloud
Google Cloud
Google Cloud
HashiCorp
Microsoft
Microsoft
Microsoft
McKinsey.org
// 06 — Projects
// Transmit
Reach me directly about collaborations or any problem you are working on.
