Skip to content
TQT
Email

Projects

Products, platforms, and engineering systems.

Omni-Agent is the flagship Applied AI platform. IQP demonstrates enterprise Quality Engineering delivery, while the remaining projects show banking automation, model development, and earlier Product Engineering foundations.

9
case studies
4
evidence groups
2
featured systems

Featured systems

The strongest evidence of Product Engineering, backend architecture, and Applied AI delivery.

2 entries
Omni-Agent — AI Platform abstract technical panel
Flagship AI Platform 2026–Present

Omni-Agent — AI Platform

Platform for building knowledge bases, running AI agents, and evaluating agent behavior

A modular Applied AI platform featuring document intelligence with Docling and Qdrant, a Streamable HTTP MCP server, a LangGraph-based multi-agent runtime, and an integrated Agent Assurance evaluation engine.

Outcome: Designed and implemented the platform foundation, including explicit domain ownership, versioned document lifecycles, asynchronous processing contracts, and integrated Agent Testing. Its Agent Assurance module won 2nd place at IVS Hackathon 2026.

LangGraphFastAPIModel Context Protocol (MCP)OpenTelemetry (OTel)LLM-as-a-JudgeQdrantDoclingDjango/DRFCelery
IQP — Intelligent Quality Platform abstract technical panel
Enterprise Applied AI 2026

IQP — Intelligent Quality Platform

AI-assisted traceability and code intelligence for enterprise systems

An enterprise platform combining graph-based product knowledge, source-code intelligence, and hybrid retrieval to automate engineering traceability and test analysis.

Outcome: Contributed to a working enterprise platform that unified product knowledge, source-code context, AI-assisted retrieval, and quality-analysis capabilities.

FastAPIQdrantPostgreSQLRedisCeleryMCP

Applied AI systems

Products and prototypes combining models, retrieval, agent workflows, and user-facing software.

3 entries
Agent Assurance (ATA) — AI Agent Evaluation Platform abstract technical panel
Evaluation Infrastructure · 2nd Place IVS Hackathon 2026

Agent Assurance (ATA) — AI Agent Evaluation Platform

Quality & evaluation infrastructure for autonomous AI agents

An independent validation and audit layer for agentic systems that captures runtime interactions via LiteLLM and OpenTelemetry, reconstructs execution traces, and enforces deterministic quality gates.

Outcome: Awarded 2nd Place at IVS Hackathon 2026 for autonomous agent verification; validated the core architecture before integration into Omni-Agent.

Agent EvaluationOpenTelemetryLLM-as-a-JudgeFastAPICeleryLiteLLM Gateway
APIT — Agent Programmatic Integration Testing abstract technical panel
AI evaluation 2025

APIT — Agent Programmatic Integration Testing

An AI-assisted API testing application

An AI-assisted API testing application that generates structured test scenarios from API documentation.

Outcome: Achieved a 0.655 macro-F1 score on structured API test-case generation using a fine-tuned Qwen-2.5-3B model via LoRA.

LLM fine-tuningLoRAQwenRAGAPI TestingEvaluation
Applied AI system 2025

E-Commerce AI Assistant

Vector search and conversational product discovery

An end-to-end AI shopping assistant that combines filtered vector search and agent-driven conversational retrieval for natural-language product discovery.

Outcome: Delivered a containerized prototype covering semantic search, conversational consultation, persistence, caching, and service orchestration.

FastAPILangGraphLangChainMilvusPostgreSQLRedis

Quality Engineering delivery

Enterprise automation, transaction validation, and quality-analysis work across complex systems.

1 entries
Industry delivery 2024-2026

Core Banking & Payment Hub QA Automation

Historical Core Banking and Payment Hub validation work

Client delivery work covering Core Banking and Payment Hub integrations across API, database, web, mobile, regression, and automation testing.

Outcome: Delivered confidential banking validation work across transaction integrity, regression, API, database, web, and mobile systems.

Core BankingPayment HubKatalonPostmanSQLJMeter

Engineering foundations

Earlier full-stack and machine-learning projects that established the foundation for the current direction.

3 entries
LMS — Learning & Assessment Platform abstract technical panel
Early Product Engineering 2024

LMS — Learning & Assessment Platform

A Django learning platform with a separate AI-assisted monitoring service

A full-stack learning and assessment platform covering structured course content, enrollment, quizzes, reporting, role-based workflows, and a separately deployed face-detection service.

Outcome: Built the initial product independently, then continued as a primary developer when its core design was adopted into a larger team implementation.

DjangoFastAPIPyTorchDocker ComposeNginxCloudflare Tunnel
Self-driving Car Problem abstract technical panel
Earlier AI research 2024

Self-driving Car Problem

YOLOv8 perception, lane segmentation, and PID control in simulation

A simulated autonomous-driving pipeline combining YOLOv8-based perception, lane segmentation, OpenCV processing, and PID steering control inside a Unity environment.

Outcome: Completed the simulation benchmark in 125.8 seconds with full marks.

YOLOv8PyTorchOpenCVComputer VisionSegmentationPID Control
Leaf-Based Plant Disease Detection abstract technical panel
Earlier computer vision system 2024

Leaf-Based Plant Disease Detection

PyTorch classification with segmentation-assisted preprocessing and visual explanations

A PyTorch computer-vision pipeline for plant disease classification that combines image preprocessing, CNN inference, class-specific thresholds, and Grad-CAM++ explanations behind a FastAPI service.

Outcome: Implemented an end-to-end computer-vision prototype covering data loading, training, inference, explainability, and API integration.

PyTorchTorchvisionResNetGrad-CAMFastAPISQLite