Jul 15, 2026
Jul 15, 2026
Fitter Health
Sole engineer across a 106-table healthcare platform, 135 passing tests, AWS delivery, and durable notification recovery.
View projectClient deliveryFull stack
Projects
The problem, the build, and the decisions along the way.
May 10, 2026
May 10, 2026
Multilingual RAG
Designed tenant-scoped retrieval with local multilingual embeddings, 6 task templates, JWT identity, usage quotas, and grounded generation.
View projectRAG and AICustomer data isolation
Jun 20, 2026
Jun 20, 2026
Realtime data
Built 3 data layers, an hourly orchestration path, and a 4-table sales star schema using Kafka, Spark, Airflow, and PostgreSQL.
View projectData engineering
Jul 1, 2026
Jul 1, 2026
Movie discovery
Built a 3-signal hybrid recommender with separate training, versionable artifacts, FastAPI serving, and optional Redis cache.
View projectMachine learning project
Sep 29, 2026
Sep 29, 2026
Document Q&A — building a retrieval system that knows when not to answer
Designed a 768-dimensional pgvector search pipeline with 3 API operations, bounded retrieval, batch ingestion, and failure-aware generation.
View projectPersonal prototype
Sep 29, 2026
Sep 29, 2026
Expiring URL service — designing a small API around explicit failure modes
Implemented 8-character aliases, create/redirect/lookup operations, scheduled expiry, and a health endpoint in Express.
View projectPersonal prototype
Learnings
Experiments and learning repositories where I explore algorithms, machine learning, data foundations, and embedded systems.
Algorithms in Python and Java
Implemented data structures and algorithms in Python and Java to study correctness and computational cost.
Edge ML — splitting an autoencoder between a device and the cloud
Trained a compatible encoder/decoder pair, deployed the encoder toward embedded inference, and connected encoded sensor payloads to a Flask decoder on AWS EC2.
ESP32 temperature inference — proving the model/firmware contract
Connected Python model training and export with a real ESP32 inference path and Flask reconstruction, including a fixed scaler and a two-value latent vector.
ML foundations — reproducible experiments before model complexity
Built inspectable pandas/scikit-learn regression workflows, trained and reloaded a persisted model, and examined how evaluation splits affect claims of model quality.
Let’s talk
I like working through complex problems with people who care about the details. Have a product to build, an engineering role, or an interesting challenge? Let’s start a conversation.
SaaimOpen to full-time roles, contract work, and conversations about things worth building.