R&D Lab
Experiments & explorations.
Where ideas get pressure-tested before they reach production.
20 projects · shipped tools, prototypes and research
Experiments
Local LLM GPU Benchmark: RTX 5090 vs DGX Spark
Same model (Gemma 4 26B), same Ollama version, same agent request: ~15 s on an RTX 5090 against ~41 s on a DGX Spark. Memory bandwidth (1,792 vs ~273 GB/s) mattered more than memory size once the model fit.
Hybrid Product Search (BM25 + Vector + RRF)
Solr 9 engine fusing keyword and kNN vector results with Reciprocal Rank Fusion. In-process ONNX embeddings, rule-based NLU over a live catalog vocabulary, typo tolerance, price parsing and multi-item queries.
On-Demand ISR: Next.js 16 + .NET
Static pages with zero API calls per view, kept fresh by signed webhooks from .NET that expire exact cache tags. Handles new and deleted pages without a rebuild.
MCP Server for Code & Database Intelligence
Gives AI assistants a map of large C# codebases: Roslyn analyses whole solutions (classes, methods, dependencies, stored procedures used, complexity) and SQL Server catalogue views supply tables, keys and procedures. Scheduled per-workspace syncs store it in MongoDB, exposed as 40+ MCP tools with a Blazor dashboard and live logs.
10-Node Bare-Metal "VMSS" Cluster
Design for a VMSS-style cluster on ten 8 GB mini PCs: Proxmox, NFS shared storage and Docker Swarm now, with a path to K3s once autoscaling is needed.
API Load Testing & Observability
Designed repeatable k6 suites for critical APIs wired into Grafana dashboards to validate SLAs and guide capacity planning.
Advanced RAG for Internal Docs
RAG pipeline for internal docs: developers query in natural language and get precise answers with source links.
Self-Hosted Web Analytics
Google Analytics replacement for an e-commerce site: a drop-in JS tracker, ASP.NET Core ingestion API, ClickHouse event store and Grafana dashboards, with natural-language querying planned.
MongoDB Query Tuning for a Meeting Platform
Compound and unique indexes on the conversations collection turned full collection scans into index scans. User-conversation queries dropped from 500–2000 ms to 5–50 ms.
Voice / IVR Agent over RAG
Fully self-hosted voice loop in front of the existing chatbot: Silero VAD, streaming whisper.cpp, Piper TTS and Pipecat orchestration, with Asterisk for SIP telephony.
In-Browser LLM Inference with WebLLM
Run small models (Qwen2.5 1.5B, Phi-3 mini, SmolLM2) in the browser via WebGPU as a "local mode" for the chatbot, optionally grounded by backend vector search.
Image & Table Extraction with Document AI
Proofs of concept extracting structured data from scanned documents: Google Document AI table parsing in .NET, and a Gemini vision-model web app with a Next.js front end.
Legacy jQuery Site → Next.js Static Export
Lift-and-shift of a jQuery + jsrender site into Next.js with output: export, keeping the CSS, behaviour and URLs byte-identical, converted in parallel page batches.
Custom Roslyn Analyzer
Build-time C# diagnostics enforcing house rules: no Console.WriteLine in favour of a logger, camelCase locals and a null-check heuristic.
PDF Generation from HTML in C#
Production solution for generating PDFs from HTML using PuppeteerSharp and iTextSharp with pixel-accurate rendering.
AI Code Review Assistant
CI/CD-integrated tool using a custom LLM to review PRs for quality, style and potential bugs, cutting manual review time by 30%.
IoT Predictive Maintenance PoC
Industrial IoT PoC predicting equipment failures via sensor data + ML using MQTT ingestion and .NET backend analysis.
End-to-End Encryption Layer
Document sharing system with E2EE ensuring only authorized users access sensitive data via secure cryptographic protocols.
RabbitMQ Microservices Bus
Async messaging layer using RabbitMQ for reliable service-to-service communication with dead-letter queues and retries.
gRPC Service Mesh
High-performance inter-service communication using gRPC with Protocol Buffers for strongly-typed microservice contracts.