Applied AI Implementation & Software Engineering

Applied AI, automation, and software systems built for real operational workflows.

I build AI-enabled applications, Python and FastAPI services, data/reporting workflows, and ML delivery systems with deterministic baselines, runnable paths, tests, screenshots, and documented outputs.

View project library GitHub profile Credentials

Applied AI implementation with bounded model use

Python, FastAPI, CLI, and reporting systems

Data workflows with runnable artifacts

Current warehouse automation commissioning context

Tests, docs, screenshots, and release notes

Interactive review mode

Choose how to inspect the portfolio.

The interaction changes the evidence path instead of only changing colors: scan the systems, inspect the technical proof, or connect the work to current engineering practice.

System overview

Start with the strongest Applied AI and engineering evidence.

Begin with the flagship AI-enabled applications and engineering systems, then inspect their public repos, case-study pages, tests, and boundaries. Private research stays labeled and limited to safe context.

Applied AI implementations

Flagship systems

Public GitHub repos

Private-safe labels

Review projects GitHub Credentials

Evidence map

6 public / 2 private

AI Nutritionist

Python / Streamlit

repo

OpsForge Suite

Next.js / FastAPI

private

OpsForge Planning Workspace

Python / CLI

repo

OpsForge Market Intelligence

Python / Typer

repo

About

Applied AI implementation grounded in software engineering discipline.

I build applied AI implementations and software systems that combine model-assisted capabilities with dependable application workflows. The portfolio covers AI-enabled planning and review tools, recommendation systems, Python and FastAPI services, reporting pipelines, and ML delivery. In my current role as a Software Commissioning Engineer, I work with warehouse automation and intralogistics systems across testing, troubleshooting, SQL/Linux environments, validation, documentation, and operational handover. That production-facing experience shapes how I design personal projects: bounded AI use, deterministic fallbacks, clear interfaces, reviewable outputs, and evidence that the system works.

Applied AI implementation

Automation

Backend/data workflows

ML delivery

Experience

Current engineering context: warehouse automation, commissioning, and operational validation.

The project work follows the same delivery habits I use in commissioning: clear run paths, tested changes, documented outputs, system validation, and handover-ready evidence.

Current role

Software Commissioning Engineer

LAS Solutions SA, member of KNAPP group

Mar 2026 - Present

Cholargos, Attica, Greece

Software commissioning work for warehouse automation and intralogistics systems, focused on turning configured software into tested, documented, handover-ready operational flows.

Support software testing, troubleshooting, configuration, and system validation for warehouse automation environments.

Work with SQL and Linux-based environments during commissioning and operational handover activities.

Document issues, test results, commissioning progress, and handover context so technical teams can review and act on the work.

Apply the same operational engineering discipline to portfolio work across applied AI implementation, automation, reporting, and backend/data workflows.

Warehouse automationIntralogisticsSQLLinuxTestingTroubleshootingSystem validation

Projects

Applied AI implementations, engineering systems, and delivery proofs.

The project library combines AI-enabled applications with backend, automation, reporting, and ML delivery work. Projects are grouped by maturity and evidence, with public source links only where intentionally ready.

Public repos

6

Runnable paths

6

Project pages

8

Private pages

2

Start here

Strongest Applied AI and software engineering entry points.

Full library

AI Nutritionist

Benchmark project: local Streamlit/CLI/FastAPI recommender with generated meal-plan proof, Hybrid Recommender V2, weekly planner summaries, model/data cards, Dockerfile healthcheck, CI, and 95 pytest tests.

OpsForge Suite

Integrated operations platform with planning workspace, review queue, reporting center, audit trail, exports, verified Docker Compose smoke, and seeded demo evidence.

OpsForge Planning Workspace

Product-planning workflow that turns rough operational briefs into structured dossiers, saved runs, compare notes, and export manifests.

Project explorer

Neural nutrition recommender

AI Nutritionist

Public

Local nutrition planner that generates daily and weekly meal plans from USDA/FNDDS data, a Mediterranean/Greek extension, a reviewed recipe-backed pilot, Hybrid Recommender V2 ranking, bounded weight-loss targets, local feedback, flat and ingredient grocery exports, Streamlit, CLI, FastAPI, and 95 pytest tests.

Impact

Generates daily and weekly meal plans with profile targets, weekly planner summaries, bounded weight-loss targets, diet-mode guardrails, alternatives, flat grocery export, recipe ingredient export, and local feedback.

Public RepoML RecommenderFastAPI95 Tests

PythonStreamlitFastAPIPandasscikit-learnUSDA FoodData Central

Validation

95 pytest tests

Ruff + mypy

GitHub Actions CI

Case study Repo ZIP

Neural nutrition recommender

AI Nutritionist

Public

Local nutrition planner that generates daily and weekly meal plans from USDA/FNDDS data, a Mediterranean/Greek extension, a reviewed recipe-backed pilot, Hybrid Recommender V2 ranking, bounded weight-loss targets, local feedback, flat and ingredient grocery exports, Streamlit, CLI, FastAPI, and 95 pytest tests.

Impact

Generates daily and weekly meal plans with profile targets, weekly planner summaries, bounded weight-loss targets, diet-mode guardrails, alternatives, flat grocery export, recipe ingredient export, and local feedback.

Public RepoML RecommenderFastAPI95 Tests

Validation

95 pytest tests

Ruff + mypy

GitHub Actions CI

PythonStreamlitFastAPIPandasscikit-learn

Case study Repo ZIP

Operations software platform

OpsForge Suite

Private

Private local-demo platform that combines planning workspace, operations review queue, reporting center, scoped memory/cache, audit trail, and export handover flows in a production-shaped Docker Compose stack.

Impact

Turns multiple smaller portfolio ideas into one coherent operations platform with planning, review, reporting, audit, and handover modules.

Private RepoDocker SmokeFastAPI + Next.jsPostgreSQLSeeded DemoExport Packages

Validation

13 backend tests

Docker Compose smoke

API contract checks

Next.jsFastAPIPostgreSQLDocker ComposeSQLAlchemy

Case study

CaseForge Studio local web app showing a generated implementation blueprint

Operational implementation planning

OpsForge Planning Workspace

Public

Public planning workspace that turns operational software briefs into implementation dossiers, architecture notes, risk registers, test plans, saved-run comparisons, and export manifests.

Impact

Turns rough operational implementation briefs into handover-ready planning artifacts before build work starts.

Public RepoPlanning WorkspaceDeterministic CoreDocker

Validation

24 unittest tests

Package build

OpsForge module contract test

PythonCLIHTTP APIlocal web UIunittest

Case study Repo ZIP

Job Market Intelligence Pipeline report desktop screenshot

Repeatable reporting system

OpsForge Market Intelligence

Public

Public reporting system for fixture-backed source collection, validation, DuckDB history, source quality, run-over-run deltas, report index, and executive summaries.

Impact

Turns fixture-backed source inputs into a repeatable intelligence report with source quality, history, run-over-run movement, and a reviewer-ready report index.

Public RepoReporting SystemDuckDB HistoryCI

Validation

28 pytest tests

OpsForge module contract test

Two-run fixture demo

PythonTyperDuckDBPandasBeautifulSoup

Case study Repo ZIP

Neural nutrition recommender

AI Nutritionist

Public

Local nutrition planner that generates daily and weekly meal plans from USDA/FNDDS data, a Mediterranean/Greek extension, a reviewed recipe-backed pilot, Hybrid Recommender V2 ranking, bounded weight-loss targets, local feedback, flat and ingredient grocery exports, Streamlit, CLI, FastAPI, and 95 pytest tests.

Impact

Generates daily and weekly meal plans with profile targets, weekly planner summaries, bounded weight-loss targets, diet-mode guardrails, alternatives, flat grocery export, recipe ingredient export, and local feedback.

Public RepoML RecommenderFastAPI95 Tests

Validation

95 pytest tests

Ruff + mypy

GitHub Actions CI

PythonStreamlitFastAPIPandasscikit-learn

Case study Repo ZIP

Operations software platform

OpsForge Suite

Private

Private local-demo platform that combines planning workspace, operations review queue, reporting center, scoped memory/cache, audit trail, and export handover flows in a production-shaped Docker Compose stack.

Impact

Turns multiple smaller portfolio ideas into one coherent operations platform with planning, review, reporting, audit, and handover modules.

Private RepoDocker SmokeFastAPI + Next.jsPostgreSQLSeeded DemoExport Packages

Validation

13 backend tests

Docker Compose smoke

API contract checks

Next.jsFastAPIPostgreSQLDocker ComposeSQLAlchemy

Case study

Operational implementation planning

OpsForge Planning Workspace

Public

Public planning workspace that turns operational software briefs into implementation dossiers, architecture notes, risk registers, test plans, saved-run comparisons, and export manifests.

Impact

Turns rough operational implementation briefs into handover-ready planning artifacts before build work starts.

Public RepoPlanning WorkspaceDeterministic CoreDocker

Validation

24 unittest tests

Package build

OpsForge module contract test

PythonCLIHTTP APIlocal web UIunittest

Case study Repo ZIP

Repeatable reporting system

OpsForge Market Intelligence

Public

Public reporting system for fixture-backed source collection, validation, DuckDB history, source quality, run-over-run deltas, report index, and executive summaries.

Impact

Turns fixture-backed source inputs into a repeatable intelligence report with source quality, history, run-over-run movement, and a reviewer-ready report index.

Public RepoReporting SystemDuckDB HistoryCI

Validation

28 pytest tests

OpsForge module contract test

Two-run fixture demo

PythonTyperDuckDBPandasBeautifulSoup

Case study Repo ZIP

Additional project pages

Supporting work shown with clear scope, repo status, and review notes.

Agentic Trading Research Lab public-safe dashboard overview

Paper-only market replay research lab

Private

Agentic Trading Research Lab

Private paper-only research platform for volatile market-event study, event-harsh replay, deterministic risk gates, offline simulation, audit logs, and dashboard/report artifacts.

AI Workflow Automation Assistant home screen with provider and review boundaries

Operations intake and human review

Public

OpsForge Review Queue

Public operations intake review queue for synthetic commissioning, configuration, test-failure, handover, SQL/data-validation, and reporting-anomaly requests, now with reviewer action packages.

LinkedIn Ads Control Report with KPI cards, pacing notes, control risks, and action list

Marketing-ops control report

Public

LinkedIn Ads Control Report

Daily marketing-ops report that turns LinkedIn Ads exports into KPI health, pacing verdicts, daily movement, control risks, campaign movement, and HTML/JSON/Markdown artifacts.

ViT Pet Classification Pipeline Streamlit UI without third-party branding

Computer vision release boundary

Public

ViT ML Delivery Proof

Supporting ML-delivery project with Oxford-IIIT data preparation, ViT fine-tuning metadata, eval JSON, confusion matrix output, release checksum manifest, FastAPI/CLI/Streamlit surfaces, and explicit artifact boundaries.

Skills

The stack behind the projects

Grouped around project evidence and current practice: Applied AI implementation, backend/API work, automation, data reporting, ML delivery, Linux/SQL environments, testing, and release quality.

Capability map

Applied AI implementation

LLM and model API integration

structured outputs

provider abstraction

model-assisted workflows

prompt contracts

human review workflows

deterministic fallbacks

evaluation boundaries

selected_capability = "applied ai implementation"

output: LLM and model API integration + structured outputs + provider abstraction + model-assisted workflows

Credentials

Education, certification, and technical evidence

The credentials section is kept as a concise reference block: formal technical education, relevant commissioning training, certificates, and project evidence that support the engineering work.

BSc AI and Computer Science

Software commissioning bootcamp certificate

Public engineering project evidence

Junior Software Commissioning Engineer Bootcamp

Code.Hub / LAS Solutions

Bash, Oracle SQL/PLSQL, C++, Docker and warehouse-process simulation work.

Certificate

BSc Artificial Intelligence & Computer Science

University of Birmingham

AI, algorithms, Java, C/C++, computer vision, security, networks, and CS foundations.

English C2

University of Michigan

Professional English working proficiency.

Contact

Professional contact for project discussion and technical collaboration.

GitHub, LinkedIn, and email are available for portfolio review, references, technical discussion, and collaboration around Applied AI implementation, software engineering, automation, reporting, and backend/data workflows.

GitHub LinkedIn Email