I build reliable software and trustworthy machine learning systems.
With 6+ years of experience across SaaS, fintech, B2B, and AI-driven platforms, I specialize in quality engineering, automation, and ML system validation.
My work focuses on reducing risk, strengthening release confidence, and ensuring that both software applications and data-driven models are tested, monitored, reproducible, and production-ready.
I operate at the intersection of:
- ✅ Senior-level QA Automation
- 🔬 Machine Learning Validation & Data Quality
- 📊 Applied Data Science in Fintech & AI Systems
Applying QA rigor to machine learning systems.
- ML model performance validation (precision)
- Feature drift detection & data distribution monitoring
- Schema validation & data integrity enforcement
- End-to-end data trust: ingestion → transformation → model → API
I apply automation-first QA principles to ML systems: validation, monitoring, reproducibility, and reliability.
Ensuring software quality from requirements to release.
- Manual & automated testing for web and API systems
- Regression, functional, acceptance, accessibility, and compatibility testing
- CI/CD quality gates to improve release confidence
- Cross-functional collaboration with product and engineering teams
This foundation enables me to approach ML systems with strong engineering discipline.
Building data-driven solutions grounded in reliability.
- Time series forecasting and financial trend analysis
- NLP and Retrieval-Augmented Generation (RAG) systems
- Risk, fraud, and financial modeling
- Enterprise ELT pipelines with validation and monitoring
My differentiator:
I don’t just build models:- I ensure they are validated, explainable, and production-trusted.
🔗 [Repo Link]
- Designed automated validation framework for ML pipelines
- Implemented feature drift detection and anomaly monitoring
- Enforced schema validation and data integrity checks
- Integrated validation into CI/CD workflows
- Ensured end-to-end model trust from raw data → warehouse → model → API
🔗 [Repo Link]
- End-to-end HR workflow automation reducing regression effort by 50%
- Maintainable BDD framework integrated with CI/CD pipelines
- Demonstrates scalable automation architecture
🔗 [Repo Link]
- Full functional and regression automation
- Page Object Model design
- Multi-environment execution with reporting
- Time series forecasting system for portfolio allocation
- Extracts trend, volatility, momentum, and risk signals
- Provides robust, statistically validated insights for financial decision-making
🔗 [Repo Link]
- Enterprise NLP system with Retrieval-Augmented Generation
- Semantic search with explainable outputs
- Designed with validation and reliability principles
- YOONO: Reduced report errors by 35% through automation
- Engage2Excel: Automated 60% of workflows, cutting regression effort in half
- 15Wins Venture: Mentored founders, improving MVP validation success by 20%
- Senior-level QA ownership with measurable automation impact
- Specialized in ML system validation and data reliability
- Strong bridge between QA, ML, product, and engineering teams
- Experience across fintech, SaaS, AI, and analytics platforms
- Focused on building systems that are not just functional, but trustworthy