I build intelligent, scalable, cloud-native systems
combining backend engineering, machine learning, and DevOps.
๐ Website ยท ๐ผ LinkedIn ยท โ๏ธ Email
RAG-as-a-Service ยท Chat + API + SDK
A managed RAG platform where companies upload their data and instantly get a chat application, API, and SDK without building ingestion, indexing, retrieval, evaluation, or cost-control pipelines themselves.
Key capabilities
- Async ingestion for PDFs, documents, and URLs
- Configurable chunking and embedding pipelines
- Vector search and filtering using PostgreSQL + pgvector
- Versioned retrieval indexes with rollback and reindexing
- Streaming chat with citations, confidence indicators, and safe โI donโt knowโ
- Evaluation datasets with regression detection
- Token usage tracking, budgets, BYOK and hybrid billing
Tech stack
Application-Level AI Governance ยท SDK + VS Code Extension
A developer-first AI usage control platform that enforces limits, budgets, and policies directly inside application code rather than at the infrastructure or proxy level.
Key capabilities
- Python and TypeScript SDKs wrapping LLM calls
- Per-user, per-feature, and per-plan usage limits
- Per-request cost caps and budget protection
- Centralized audit logs with blocking reasons
- VS Code extension for real-time usage inspection
- BYOK support with consistent tracking
Tech stack
Market Forecasting Platform (Founder Project)
A production-grade market forecasting platform delivering multi-horizon probabilistic predictions (24H, 30D, 12W, 12M) with confidence scoring, alerts, and historical forecast-vs-actual analysis.
Key capabilities
- Rolling inference pipelines with hourly and daily refresh cycles
- XGBoost-based forecasting with uncertainty estimation
- Authenticated dashboards for forecasts, alerts, and performance tracking
- Subscription billing with plan-based feature enforcement
- Cloud infrastructure deployed with Terraform and CI/CD
Tech stack
- Python
- TypeScript
- JavaScript
- Go
- PostgreSQL
- MySQL
- MariaDB
- Microsoft SQL Server
- MongoDB
- Amazon DynamoDB
- Amazon Aurora
- Amazon S3
- Redis
- pgvector
- FastAPI
- Django
- Node.js
- Express.js
- NestJS
- REST APIs
- WebSockets
- Background workers and async processing
- Go (backend services)
- React
- Next.js
- Component-based UI architecture
- Server-side rendering and performance optimization
- TensorFlow
- PyTorch
- Scikit-learn
- XGBoost
- MLflow
- Pandas
- NumPy
- Time-series forecasting and regression models
- AWS (EC2, S3, RDS, ECS, Lambda, SageMaker)
- Docker
- Kubernetes
- GitHub Actions
- Infrastructure as Code (Terraform)
- Monitoring, logging, and cost optimization
- End-to-end systems from idea to architecture to production
- Scalable, cloud-ready, AI-powered platforms
- Clean, maintainable, and well-documented code
- Reliable execution and clear communication