AI/ML Engineer building production ML and GenAI systems with a focus on RAG, AI agents, evaluation, APIs, observability, and decision-support workflows.
| Project | Highlights |
|---|---|
| Evagix | Local-first evidence validation for AI-assisted repositories with explainable findings, traceable evidence, separate evidence and policy layers, and CLI workflows |
| RAG QA Command Center | CI-tested RAG evaluation across 3,824 QA runs and 93,375 retrieval events, with retrieval diagnostics, hallucination-risk review, trace inspection, configuration comparison, and policy simulation |
| LLMOps Telemetry Command Center | Reliability, latency, cost, routing, and drift analysis across 9,000+ offline interactions, 1,595 sessions, and 438 user profiles, with triage thresholds and evidence exports |
| Fraud Risk Ops Platform | FastAPI inference and analyst review with calibrated Random Forest and XGBoost models, validation F1 scores of 0.882 / 0.876, threshold policies, audit logs, batch jobs, and Prometheus/Grafana monitoring |
| Advanced ML Sentiment Lab | Reproducible NLP workflows with TF-IDF modeling, ROC-AUC/PR-AUC evaluation, threshold tuning, error review, live prediction, and exportable artifacts |
| Pima Diabetes Pipeline | End-to-end tabular ML pipeline with EDA, feature engineering, calibration, cost-aware thresholding, evaluation, and deployable artifacts |
| Area | Engineering scope |
|---|---|
| Production ML systems | Reproducible pipelines, calibrated predictions, threshold policies, deployable artifacts, APIs, and monitoring |
| Generative AI & RAG | Retrieval evaluation, embeddings, reranking, source attribution, grounded generation, structured outputs, and quality checks |
| AI Agents & automation | Tool calling, workflow orchestration, controlled execution, stateful workflows, and human review where needed |
| Evaluation & reliability | RAG, LLM, and agent evaluation, benchmark design, regression testing, trace review, quality checks, and operational triage |
| APIs & serving | FastAPI services, strict schemas, PostgreSQL, Redis, background jobs, and CI-backed delivery |
| Applied ML & analytics | NLP, tabular ML, computer vision, threshold optimization, explainability, analytics, and decision-support workflows |
| Project | Focus |
|---|---|
| Road Accident Risk Prediction | Two-stage risk scoring with LightGBM, XGBoost residual modeling, NNLS blending, stable OOF evaluation, and interpretable risk features |
| Clinical Deterioration Early Warning | 12-hour deterioration baseline with tabular models, probability ensembling, and cost-based threshold policy tables |
| Cancer Risk Analysis | Synthetic tabular data, validation, leakage-aware benchmarking, and interpretable risk modeling |
| SMS Spam Detection | Dual TF-IDF pipeline with calibrated Linear SVM, nested CV, threshold tuning, explainability, and robustness checks |
| Project | Focus |
|---|---|
| Health Intelligence Platform | Behavioral risk analytics, cohort KPIs, threshold diagnostics, feature importance, trends, and scenario simulation |
| Short-Video Intelligence Dashboard | Virality scoring, engagement metrics, creator leaderboards, timing patterns, and segment benchmarks |
| EV Charging Analytics | Geospatial infrastructure analytics, fast-DC allocation scenarios, market slices, and network planning |
| Football Matches Dashboard | European football and UCL analytics with KPIs, standings, team exploration, head-to-head analysis, and interactive match tables |
| Project | Focus |
|---|---|
| Old Photo Restorer | Gradio computer vision app with GFPGAN restoration, optional upscaling, before/after preview, and batch ZIP export |
| Hugging Face QuickStart Tool | Gradio utility that converts Hugging Face model and repository URLs into run commands, download snippets, file views, risk hints, and project scaffolds |
| Dataset | What it enables |
|---|---|
| RAG QA Logs & Corpus | QA logs, retrieval events, corpus documents, and evidence-style data for RAG evaluation workflows |
| LLM Production Telemetry | Offline LLMOps telemetry for reliability, latency, cost, routing, drift, and triage-policy analysis |
| Cancer Risk Factors | Synthetic health, lifestyle, environmental, and genetic features for leakage-aware risk modeling and analysis |
| Global EV Infrastructure | Standardized EV charging data for geospatial analytics, infrastructure planning, and network modeling |
| YouTube Shorts & TikTok Trends 2025 | Short-form content data for trend exploration, creator benchmarks, and virality analysis |
| Digital Lifestyle & Mental Wellness | Behavioral signals for wellbeing analytics, cohort exploration, and predictive workflows |
| Category | Tools |
|---|---|
| Languages & Core |       |
| Data & Analytics |      |
| ML / DL |      |
| GenAI / RAG / Agents / CV |             |
| Apps & Interfaces |        |
| APIs & Serving |          |
| Infrastructure & Deployment |      |
| Evaluation, Monitoring & Quality |          |
Curated repositories and references across AI/ML, RAG, agents, backend, infrastructure, systems, and developer tooling.
Browse my GitHub Stars & Lists →
- 🚀 Production ML & GenAI systems: FastAPI services, Dockerized delivery, evaluation workflows, observability, and maintainable production systems
- 🧠 RAG reliability: retrieval evaluation, grounded answers, source attribution, guardrails, regression tests, and trace review
- 🗂️ Validated data products: clean schemas, documented pipelines, reusable notebooks, and ML-ready artifacts
- 📊 Decision-support tooling: monitoring, threshold policies, operator-facing interfaces, and practical review workflows
Best contact: LinkedIn