Portfolio / work

Built, building, and intentionally next.

A clearer project archive: shipped systems first, active work second, future directions last. Each card points back to a public source where one exists.

Built · GenAI

Hybrid RAG API

FastAPI + Ollama exploration of retrieval, local inference, memory and modular APIs.

Python · FastAPI · OllamaGitHub ↗
Built · ML

CloudCostAI

Applied ML project for cloud-cost prediction, with a Flask interface and prediction workflow.

Python · ML · FlaskGitHub ↗
Built · Security

NmapAnalyzer

C-based network scanning and analysis tooling connected to MySQL for structured scan results.

C · Nmap · MySQLGitHub ↗
Built · Security automation

ReconX

Web reconnaissance automation project built around common enumeration tooling.

Node.js · FFUF · GobusterGitHub ↗
Built · ML

LoanApprovalAI

Classification project for learning the practical workflow around preprocessing, training and inference.

Python · scikit-learnGitHub ↗
Built · Security / AI

Autonomous Red Team Project

Local-LLM-oriented security automation experiment exploring planning and tool orchestration.

Python · Ollama · SecurityGitHub ↗
Active · Local AI

LocalForge

Building a local-first AI developer environment around locally running models, extension workflows and GPU-aware execution.

Local LLMs · DevToolsGitHub ↗
Active · Developer tooling

GNCore

A Python package exploring reusable AI/LLM skills, workflows, prompts and automation-oriented developer tooling.

Python · LLM toolingPyPI ↗
Research · 3D cadastre

3D ULPIN Mapping System

Research and prototype direction for a backward-compatible volumetric extension of India’s ULPIN framework.

3D · GIS · AIRead research →
Active · Learning

AI/GenAI Engineering Track

Systematic progression through neural networks, PyTorch, transformers, RAG, agents, fine-tuning, inference and deployment.

PyTorch · Transformers · RAGSee journey →
Future direction

Production local-AI stack

GPU-backed local inference, model discovery, developer tooling, evaluation, serving and deployment as one cohesive system.

GPU · Inference · MLOpsPlanned
Future direction

AI systems observability

Evaluation and monitoring patterns for local and cloud LLM systems: latency, quality, failures, cost and reproducibility.

Evals · Tracing · MetricsPlanned