From One Model to Many Systems
It started with a single CNN. Each project after it answered a harder question than the last — here's the path, milestone by milestone.
Where it began — proving a model could shoulder a life-or-death triage decision.
PneumoAI — Pneumonia Detection CNN
Triage classification and region localization for emergency lung scans.
Radiology departments experience high backlogs, delaying critical diagnosis.
A custom CNN built in PyTorch to classify pneumonia cases and generate Grad-CAM heatmaps to prioritize emergency scans.
- DICOM IngestionParses raw clinical imaging datasets.
- Grad-CAM HeatmapsHighlights consolidation areas to assist review.
- Loss OptimizationUses weighted cross-entropy to handle class imbalance.
PneumoAI — Pneumonia Detection CNN
Where it began — proving a model could shoulder a life-or-death triage decision.
Triage classification and region localization for emergency lung scans.
Radiology departments experience high backlogs, delaying critical diagnosis.
A custom CNN built in PyTorch to classify pneumonia cases and generate Grad-CAM heatmaps to prioritize emergency scans.
- C++ Core EngineProcesses recursive snapshots in microseconds.
- 60fps AnimationsRenders visual data changes with zero jank.
- Interactive CanvasCustom graphical graph and tree builders.
The leap into systems — trading JavaScript's ceiling for compiled C++ speed.
AlgoPlus — Cinematic DSA Visualizer
High-performance hybrid compiled algorithm snapshots.
Client-side JS visualizers suffer massive layout lag on large array computations.
A fast hybrid engine running compiled routines in C++ with uvicorn FastAPI routes.
AlgoPlus — Cinematic DSA Visualizer
< 1msHigh-performance hybrid compiled algorithm snapshots.
Learning to move at the speed of the market — push, never poll.
CoinPush — Crypto Screening Terminal
Cryptocurrency tracking dashboard powered by live WebSockets.
Market watchers experience lag and heavy network request usage due to standard REST API polling.
A fast cryptocurrency screen terminal fetching live pricing updates via continuous WebSockets.
- Auto-ReconnectionKeeps WebSocket state alive during temporary network dropouts.
- SWR Query CachesPrevents duplicate API requests across UI elements.
- Pre-cached LayoutsMinimizes paint latency on initial render.
CoinPush — Crypto Screening Terminal
90%Cryptocurrency tracking dashboard powered by live WebSockets.
- Stochastic Scipy CoreRuns high-iteration wealth distribution paths in Python.
- Offline FallbackComputes mathematical growth curves locally if API connection drops.
- BFF AuthenticationImplements secure backend-for-frontend routes.
Turning uncertainty into something you can see — ten thousand futures, one decision.
WealthyMinds — Probabilistic Wealth Engine
A financial modeling tool integrating AI guidance with Monte Carlo projections.
Individual investors frequently lack access to complex statistical simulations to visualize risk ranges.
An analytical app linking Gemini 2.0 advisory prompts with a Monte Carlo modeling backend.
WealthyMinds — Probabilistic Wealth Engine
10kA financial modeling tool integrating AI guidance with Monte Carlo projections.
Building for people under pressure — real-time feedback the moment it matters.
InterviewPilot — Speech & Telemetry Trainer
A collaborative mock interview app featuring real-time AI speech feedback.
Candidates face high preparation anxiety and lack real-time feedback on mock responses.
A collaborative team project where I engineered the AI speech integration and client-side expression detection pipeline.
- WebSocket SpeechLow-latency audio feedback loop powered by Gemini and Vapi.
- MediaPipe WorkersProcesses webcam frames off-thread to maintain smooth animations.
- Performance MetricsAggregates candidate scoring data using Prisma ORM.
InterviewPilot — Speech & Telemetry Trainer
Val Loss: 0.08A collaborative mock interview app featuring real-time AI speech feedback.
- Unified AdaptersInterfaces Google AI, Groq, and local Ollama.
- Onion MiddlewarePipeline tracing and validations via Zod structures.
- Local FailoverAutomatically falls back to Ollama if external APIs time out.
Graduating from shipping apps to shipping the infrastructure others build on.
Vectrion — AI Application SDK
Modular TypeScript library for developer tool abstractions.
Developers write duplicate middleware for prompt routing, logging, and validations.
A typed SDK offering clean adapter routing, prompt verification, and local fallback paths.
Vectrion — AI Application SDK
< 0.5msModular TypeScript library for developer tool abstractions.
Making the invisible visible — governing architecture before it quietly rots.
ArchLens — Architecture Intelligence
Continuous, evidence-based structural governance and dependency graph analysis for software repositories.
Software architecture degrades silently, leading to build-time bloat, circular dependency paths, and architectural debt that linters cannot detect.
A monorepo-based AST parser and dependency graph builder that enforces module rules and calculates explainable structural health scores.
- Dependency CyclesDeterministic cycle detection across multi-package codebases.
- Structural ParsingMulti-stage AST parser resolving module-level import/export graphs.
- Governance RulesEnforces layer restrictions and score thresholds directly in CI/CD quality gates.
ArchLens — Architecture Intelligence
0 CycleContinuous, evidence-based structural governance and dependency graph analysis for software repositories.
- Multi-Stage PDF PipelineCombines pdfminer and PyMuPDF fallback for perfect document intelligence.
- Vector RAG LayerStores historical question papers in ChromaDB for high-precision semantic recall.
- Structured LiteLLM RoutingFeatures zero-parse-failure Pydantic outputs backed by Groq APIs.
Teaching documents to answer questions — retrieval over guesswork.
Exyst — AI Exam Intelligence
Predictive exam analytics engine leveraging LLM-based page classification and ChromaDB semantic RAG pipelines.
Students and educators struggle to extract key focal areas from dense, unstructured historical question papers and university syllabi.
An intelligent processing pipeline parsing PDFs, classifying sections, indexing question embeddings via ChromaDB, and predicting exam papers.
Exyst — AI Exam Intelligence
91.4%Predictive exam analytics engine leveraging LLM-based page classification and ChromaDB semantic RAG pipelines.
Closing the loop — models that defend revenue, measured in real rupees.
TeleChurn — Churn Prediction Terminal
Interactive FastAPI web dashboard and machine learning pipeline forecasting telecom subscriber churn.
Telecom operator teams lack early, regional-level forecasts of customer MoM subscriber declines to target retention budgets efficiently.
An ML classification pipeline with Optuna hyperparameter searches, SHAP interpretability, and a custom financial ROI simulator.
- Optuna XGBoost CoreMulti-model pipeline benchmarking Logistic Regression, Random Forests, and Boosted Ensembles.
- ROI Alert OptimizerDynamically models ARPU and campaign incentives to target subscribers at peak profitability thresholds.
- Circle Strategy PrescriptionsAutomatically suggests copper retirement, FTTH upgrades, or prepaid value bundles.
TeleChurn — Churn Prediction Terminal
87.2%Interactive FastAPI web dashboard and machine learning pipeline forecasting telecom subscriber churn.