Portfolio

Projects

A curated set of flagship repositories out of 250+ public projects on GitHub, grouped by domain. Search or filter to explore, or view the full catalog on GitHub.

Agentic AI & LLM Systems

44 projects

Agentic AI & LLM Systems

Agentic GraphRAG for Financial Institutions

Secure, agentic GraphRAG query systems for banking, fraud detection, tax analytics, and financial reconciliation — designed for auditability and least-privilege data access.

GraphRAGAgentic AIFinancial ServicesSecurity
View on GitHub
Agentic AI & LLM Systems

Enterprise Agentic AI Primer with n8n

Practical primer for building enterprise agentic AI workflows with n8n — covering triggers, agent nodes, tool integrations, error handling, and production deployment patterns.

n8nAgentic AITutorial
View on GitHub
Agentic AI & LLM Systems

DeepSeek V3 Enterprise Integration

Enterprise integration patterns and deployment guide for DeepSeek V3 open-weight models — benchmarking, API integration, fine-tuning, and production deployment notes.

DeepSeekLLMOpen-weightEnterprise AI
View on GitHub
Agentic AI & LLM Systems

RAG Implementation on GCP Vertex AI

Retrieval-Augmented Generation (RAG) implementation on GCP Vertex AI — document ingestion, embedding generation, vector search, and grounded LLM response generation.

RAGGCPVertex AILLM
View on GitHub
Agentic AI & LLM Systems

AWS Bedrock AgentCore — Enterprise-Scale AI Agent Deployment

End-to-end guide and reference implementation for deploying production AI agents at enterprise scale using AWS Bedrock AgentCore. Covers agent runtime configuration, memory management, tool integration, multi-agent orchestration, and AWS-native IAM/guardrails for secure, governed agentic workloads.

AWS BedrockAgentCoreAgentic AIEnterpriseCloud AI
View on GitHub
Agentic AI & LLM Systems

Google ADK

Working examples and patterns using Google's Agent Development Kit (ADK) for building agentic applications.

Google ADKAgentic AI
View on GitHub
Agentic AI & LLM Systems

Google ADK Agents — Customer Servicing & Fraud Triage

Hierarchical customer-servicing agent and a fixed-pipeline fraud-triage agent built on Google's Agent Development Kit, with PII-redaction guardrails, an audit trail, and a mandatory human sign-off before a fraud call becomes final — production-hardened with config, logging, containerization, and CI rather than left as a notebook demo.

Google ADKAgentic AIBankingGovernance
View on GitHub
Agentic AI & LLM Systems

Real-Time Conversation Signal Copilot

Streams live conversation turns, tags multi-label conversational signals (objection, buying signal, compliance risk, question, action item) with a self-consistency confidence score, retrieves grounded next-best-action recommendations from an approved knowledge base via RAG with citations, and enforces a compliance guardrail layer that withholds and flags rather than silently rewrites non-compliant output.

FastAPIWebSocketRAGGuardrailsReact
View on GitHub
Agentic AI & LLM Systems

Conversational LLM Fine-Tuning — SFT + DPO + LoRA/QLoRA

End-to-end, CPU-runnable fine-tuning pipeline that turns a small instruct model into a conversational signal classifier and compliant-response suggester: synthetic data generation, LoRA-based supervised fine-tuning, DPO preference optimization continuing the SFT adapter, an evaluation harness, and a merge/export step for serving, with a production fine-tuning and promotion playbook.

SFTDPOLoRAPEFTHuggingFace
View on GitHub
Agentic AI & LLM Systems

Golden Dataset & Evaluation Framework

Human-in-the-loop golden-dataset annotation workflow for conversational AI, with Cohen's/Fleiss' kappa inter-annotator agreement and Expected Calibration Error implemented from scratch, plus a CI-enforced evaluation gate that fails a build when a model or prompt version regresses against the golden set.

EvaluationAnnotationCalibrationCI/CD Gate
View on GitHub
Agentic AI & LLM Systems

Low-Latency LLM Serving Benchmark

Reference architecture and reproducible benchmark harness for low-latency LLM serving: a CPU baseline streaming server, real quantization and concurrency measurements, Kubernetes autoscaling manifests, and a documented vLLM/continuous-batching production path.

LLM ServingvLLMQuantizationKubernetes
View on GitHub
Agentic AI & LLM Systems

Real-Time Streaming ASR + Diarization Pipeline

Chunked audio ingestion with voice-activity-gated buffering, faster-whisper streaming transcription, and a lightweight speaker-turn diarizer, emitting timestamped speaker-attributed transcript events designed to feed directly into a real-time conversation-signal pipeline.

ASRfaster-whisperDiarizationStreaming
View on GitHub

Computer Vision & Industrial AI

11 projects

Computer Vision & Industrial AIDemo video

Industrial Social Distancing Monitor

COVID-19 social-distancing enforcement tool for industrial floors, built on YOLO with Nvidia Jetson Nano/Xavier and Raspberry Pi. GeoPandas, Fiona, and Shapely were used for floor-plan analysis and geofencing. Streamed IoT data to GCP Pub/Sub, Dataflow, and BigQuery for plant-wide analytics. Delivered at 93% lower cost than a comparable vendor solution.

Open-source beta: industrial social-distancing solution

If playback is blocked, try opening in an incognito browser window.

YOLOJetsonGeoPandasGCPEdge AI
View on GitHub
Computer Vision & Industrial AIDemo video

Computer-Vision Vaccine Vial Tracking

Vaccine-vial tracking system for healthcare manufacturing using Hough Transforms, image segmentation, and CUDA-accelerated OpenCV on a Linux HPC cluster with Nvidia GPUs and C++. Tracks vials reliably across the design pipeline through multiple manufacturing stages.

Vial pre-tracking

If playback is blocked, try opening in an incognito browser window.

Vial tracking

If playback is blocked, try opening in an incognito browser window.

OpenCVCUDAHough TransformsC++Healthcare
View on GitHub
Computer Vision & Industrial AI

YOLO vs. Vision-AI Model Benchmark

Benchmarks YOLO against CNN, Transformer, and small vision-language models across manufacturing, healthcare, and video-analytics monitoring workloads — accuracy, latency, and throughput trade-offs for real deployment decisions.

YOLOTransformersVLMBenchmarking
View on GitHub
Computer Vision & Industrial AI

RTSP YOLO Video Analytics Pipeline

Real-time video analytics pipeline: RTSP ingestion, YOLOv8 detection and tracking, configurable zone rules, and MQTT/webhook event dispatch for downstream systems.

RTSPYOLOv8MQTTReal-time
View on GitHub
Computer Vision & Industrial AI

Classical CV Inspection Toolkit

Classical OpenCV toolkit — Hough transforms, contour segmentation, and tamper detection — for industrial and security inspection use cases without a neural network in the loop.

OpenCVClassical CVSecurity
View on GitHub
Computer Vision & Industrial AI

IoT Video Event Stream Analytics

Streaming analytics service that turns vision events into rolling statistics, Z-score anomaly alerts, and a live occupancy dashboard.

StreamingAnomaly DetectionDashboards
View on GitHub

Data Engineering & MLOps

59 projects

Data Engineering & MLOps

Lakehouse Forecasting MLOps Platform

End-to-end lakehouse forecasting platform — medallion-architecture ingestion, feature pipelines, model training, and MLOps tracking for demand-forecasting workloads.

LakehouseForecastingMLOps
View on GitHub
Data Engineering & MLOpsDemo video

Real-Time IoT Data Engineering — Kafka & Spark Structured Streaming

Solution architecture for machine and IoT data pipelines — the design pattern behind the Factory Pulse Industrial-IoT proof of concept: streaming ingestion, per-machine state, rolling FFTs, and threshold-based alerting from factory-floor devices to the cloud.

Factory Pulse — Industrial IoT data platform (conceptual PoC)

If playback is blocked, try opening in an incognito browser window.

KafkaSpark Structured StreamingIIoT
View on GitHub
Data Engineering & MLOps

Kafka Stream Processing on Databricks

Reading and processing streaming data from Kafka topics into Databricks — Structured Streaming integration, checkpointing, and aggregation patterns for real-time analytics.

KafkaDatabricksStream ProcessingSpark
View on GitHub
Data Engineering & MLOps

Batch Data Processing on Databricks

Batch data processing patterns on Databricks — partitioning strategies, Delta Lake MERGE, job scheduling, and performance optimization for large-scale ETL workloads.

DatabricksBatch ProcessingDelta Lake
View on GitHub
Data Engineering & MLOps

Enterprise Kafka Orders Platform

Production-grade Kafka platform for enterprise order management — event-driven order lifecycle, topic partitioning, consumer groups, and exactly-once processing patterns.

KafkaOrdersEvent-Driven Architecture
View on GitHub
Data Engineering & MLOps

Sorter Anomaly Detection with PySpark

Industrial sorter anomaly detection pipeline using PySpark — sensor data ingestion, feature engineering, anomaly scoring, and alerting for manufacturing sort operations.

PySparkAnomaly DetectionIndustrialManufacturing
View on GitHub
Data Engineering & MLOps

Tidy Data in Python

Foundations of tidy data principles in Python — long vs. wide format, Pandas melt/pivot, and data reshaping patterns for clean analytical pipelines.

Tidy DataPythonPandas
View on GitHub
Data Engineering & MLOps

Enterprise Airflow with Docker

Production-ready Apache Airflow deployment on Docker — multi-executor setup, secret management, connection configuration, and operational best practices.

AirflowDockerOrchestration
View on GitHub

Enterprise & Financial AI

27 projects

Enterprise & Financial AI

AI Controller — From Vision to Execution

Strategic roadmap translating AI controller vision into an execution plan — capability mapping, build vs. buy decisions, partner strategy, and phased delivery milestones.

AI StrategyProduct RoadmapEnterprise AI
View on GitHub

GPU, HPC & Infrastructure

25 projects

Geospatial & Supply Chain

12 projects

Healthcare & Life Sciences AI

10 projects

Healthcare & Life Sciences AI

Enterprise Healthcare Test Data Management Platform

Full-stack, portfolio-grade Cloud Test Data Management platform for regulated healthcare (React/FastAPI/PySpark): PHI/PII discovery and deterministic masking with referential integrity across 5 heterogeneous systems, production-scale subsetting, synthetic data generation, an automated 12-gate certification pipeline, dataset lifecycle/refresh orchestration, storage/compute capacity planning, RBAC with real JWT authentication, and tamper-evident audit evidence packages. Built as an all-synthetic-data reference implementation with a 20-chapter tutorial and an honest, itemized security-limitations section.

Test Data ManagementPHI/PII MaskingFastAPIPySparkHealthcare Data
View on GitHub

Enterprise Architecture (Palantir Foundry)

12 projects

Semantic Layer, Knowledge Graphs & APIs

15 projects

Semantic Layer, Knowledge Graphs & APIs

Entity Resolution & Reconciliation Engine

Reconciles messy, multi-source infrastructure records (a CMDB export, a cloud-inventory dump, a monitoring heartbeat feed) into unified golden-record entities using custom blocking, multi-field similarity scoring, and configurable survivorship rules — with a human review queue and full field-level provenance and audit trail.

Entity ResolutionData ReconciliationFastAPIReact
View on GitHub
Semantic Layer, Knowledge Graphs & APIs

Live Infrastructure Knowledge Graph

Neo4j-backed knowledge graph and documented operational ontology for infrastructure topology, reconciling three disparate live feeds (CMDB, service-mesh discovery, telemetry) with staleness/TTL-aware conflict resolution, live WebSocket graph updates, and a blast-radius impact-analysis query.

Knowledge GraphNeo4jOntologyReal-time
View on GitHub
Semantic Layer, Knowledge Graphs & APIs

Real-Time Semantic Data Pipeline

Async staged pipeline (ingest → normalize → entity-link → enrich → publish) that turns raw, inconsistent telemetry into a live, queryable semantic layer — consumed by an example rule-based decision agent whose reasoning trace (facts read, rule fired) is shown live on the dashboard.

StreamingEntity LinkingAgent ReasoningFastAPI
View on GitHub
Semantic Layer, Knowledge Graphs & APIs

Observability MCP Gateway

A remote Model Context Protocol (MCP) server over HTTP/SSE exposing a synthetic observability dataset — logs, latency/error metrics, and alerts for five services — with bearer-token access control, built to learn the remote-MCP pattern instead of the more common local stdio server.

MCPObservabilityHTTP/SSE
View on GitHub
Semantic Layer, Knowledge Graphs & APIs

Inventory MCP Toolkit

A warehouse/inventory system exposed through the Model Context Protocol — a server (5 tools, a resource, a prompt) and a standalone client, implemented end to end in TypeScript over SQLite, to see exactly how an LLM host and an MCP server talk to each other.

MCPTypeScriptSQLite
View on GitHub
Semantic Layer, Knowledge Graphs & APIs

Fulfillment Ops API

A layered Express/TypeScript REST API over PostgreSQL modeling a warehouse network — warehouses, SKUs, orders, shipments — seeded with 50,000 realistic orders, with measured query-optimization work and a React analytics dashboard on top.

REST APIPostgreSQLTypeScript
View on GitHub
Semantic Layer, Knowledge Graphs & APIs

Service Health Dashboard

Internal-tooling dashboard for live service health — metrics, alerts, and history — built on a hand-written WebSocket layer (no socket.io) over Express/PostgreSQL so the subscription model and backpressure handling stay visible, with a continuous event simulator keeping it live by default.

WebSocketPostgreSQLReact
View on GitHub
Semantic Layer, Knowledge Graphs & APIs

Live Transcription Gateway

Real-time audio transcription gateway — browser mic capture, binary WebSocket streaming, a pluggable speech-to-text provider interface, and live partial/final transcript rendering — runnable fully offline with a mock provider, no API key required.

WebSocketReal-timeSpeech-to-Text
View on GitHub
Semantic Layer, Knowledge Graphs & APIs

Semantic Sports AI RAG

Semantic RAG system for sports data — entity extraction, semantic search over player/team/event records, and grounded question-answering with a sports knowledge base.

RAGSportsSemantic AIKnowledge Base
View on GitHub
Semantic Layer, Knowledge Graphs & APIs

Sport Ontology Knowledge Graph

Ontology-driven knowledge graph for sports data — entities, relationships, and inference rules capturing players, teams, events, and statistics in a queryable semantic model.

Knowledge GraphOntologySportsSemantic Modeling
View on GitHub
Semantic Layer, Knowledge Graphs & APIs

Sports Knowledge Graph RAG

RAG system layered on a sports knowledge graph — graph-aware retrieval, entity linking, and multi-hop reasoning for complex sports analytics queries.

Knowledge GraphRAGSportsGraph RAG
View on GitHub

Quality Assurance & Test Automation

1 project

Quality Assurance & Test Automation

Selenium & Playwright Test Automation Tutorials

6-part tutorial series on Selenium and Playwright test automation in Python — from fundamentals through pytest, CI/CD-ready patterns, and AI-agent-driven testing with Claude Code and MCP.

SeleniumPlaywrightpytestTest AutomationCI/CD
View on GitHub