ML Engineer building RAG/LLM systems, MLOps pipelines, and data engineering infrastructure that ships to production — from PHC, for the world.
I'm a freelance ML and data engineer with over three years of industry experience across RAG/LLM systems, MLOps, time-series forecasting, and data engineering. I work at the intersection of rigorous ML and production engineering — the place where good ideas become systems that actually run.
I built PLRS — an open-source Personalized Learning Recommendation System — as a production-grade product: FastAPI backend, SAKT model trained on OULAD, knowledge graph constraint layer, spaced repetition ranking, and a full CI/CD pipeline. The kind of project where every architectural decision is intentional and documented.
Outside of client work, I compete on Zindi and write technical content on ML architecture for Towards Data Science. Both keep me sharp, and both occasionally produce results worth talking about.
Open to new engagements
I work remotely and I'm selective about it — I look for environments where there's real engineering to be done, where autonomy is the default, and where the work creates measurable impact. If that sounds like your team, let's talk.
Get in TouchProduction-grade open-source edtech system: SAKT knowledge tracing model, DAG constraint layer, multi-objective ranker with SuperMemo-2 spaced repetition. FastAPI backend with 4-tier auth and sliding-window rate limiting.
↗Semantic job matching pipeline using LLM embeddings and vector search. Retrieves and ranks listings against candidate profiles with explainable scoring and source attribution.
↗End-to-end time-series forecasting for commodity and market data. Automated feature engineering, ensemble models, and live prediction endpoints with drift monitoring.
↗Production data pipeline with schema validation, incremental loading, and alerting. Multi-source ingestion with lineage tracking and idempotent transforms built for reliability at scale.