Noble Eselase Vulley/Software Engineer, applied-ml researcher & database architect

I build enterprisesoftware, and themodels that run on it.

I have spent about five years building software people rely on: payroll that has to be right, logistics that cannot go down, a system that helped run an election. I design and tune the databases sitting under a lot of it, I build, fine-tune, and research the machine-learning models some of these systems now lean on, and at AfricodeLab I help train the engineers coming up behind me.

Selected work CV / Résumé GitHub

Based: Accra, Ghana
Practice: Co-founder, AfricodeLab
Published: Springer LNNS, 2026
Open to: Contract & full-time

Profile

The short version of who I am and how I got here. I work out of Accra, Ghana.

Noble Eselase Vulley

Email: eselasenobleson@gmail.com
Phone: +233 553 851 758
Location: Accra, Ghana
GitHub: Eselase-Noble
LinkedIn: noble-vulley

I am a software engineer and applied-ML researcher, and I co-founded AfricodeLab. Most of what I do is backend and full-stack work: microservices, payment systems, and the databases sitting underneath them. The rest is research on the models a lot of those systems now depend on.

Over the last five years my work has ended up in real use across finance, logistics, education, and government. I design and tune the databases behind it, and I have led machine-learning projects on everything from medical scans to fraud to satellite imagery. What I care about is less glamorous than any of that: writing software that stays correct and stays easy to change long after it ships.

5+: Years shipping software
30+: Projects delivered
10+: Languages & frameworks
1: Peer-reviewed chapter

What I work on

Backend & distributed systems

Spring Boot and Go services that hold up when traffic does. Service discovery, API gateways, queues, and event streaming, wired together so a failure in one place does not take the rest down.

Spring Boot
Go
Kafka
Eureka
gRPC/REST

Applied machine learning

LLM fine-tuning and RAG, medical-imaging models, and plain classical ML. I like taking a model the whole way, from messy raw data to something running behind an API.

LLMs / RAG
PyTorch
FAISS / Qdrant
MedGemma

Full-stack product

Front ends in Next.js, React, Vue, and Laravel, wired to typed APIs. I try to give the screen the same attention as the service behind it, since users only ever see the screen.

Next.js
React
Vue
TypeScript

Data & databases

Schema design, indexing, and live migrations. This is where a lot of my query work lives; on systems already in production it has cut execution times by as much as 40%.

PostgreSQL
Oracle
MySQL
PL/SQL

Selected work

A mix of things I have shipped and a few research projects. Use the filters to narrow it down. The work I am most proud of is marked.

2026

Odum — Cocoa Deforestation Traceability

Helps cocoa exporters prove their beans are deforestation-free under the EU Deforestation Regulation. It reads Sentinel-2 satellite imagery to catch post-2020 forest loss at sub-hectare resolution, which is exactly where the usual 30 m datasets tend to miss smallholder farms, then produces a due-diligence statement with the evidence attached.

Python
FastAPI
PostGIS
LightGBM
Sentinel-2
Next.js

Data & ResearchPrototypeGeospatial ML & backend

2026

Sway — Influence Analytics Platform

Ranks influencers by how central they really are in a network (PageRank, eigenvector, betweenness), groups their audiences with Louvain community detection, then simulates how far a campaign would travel and picks the best people to seed it within a set budget.

Python
Neo4j
NetworkX
PostgreSQL
Next.js
scikit-learn

Full-stackProductionFull-stack & algorithms

2026

AfricodeLab ERP

An ERP suite for African businesses, put together as separate services in Java, Rust, and Python that sit behind an API gateway and talk to each other over RabbitMQ. It covers accounting, HR, procurement, CRM, and compliance, with a Next.js front end kept well clear of the backend so either side can change without breaking the other.

Spring Boot
Rust
Python
Eureka
RabbitMQ
PostgreSQL

BackendIn progressArchitecture & services

2026

IntelliFraud Copilot

A copilot for fraud analysts. Several LLM agents work a case together, pulling from policy documents with hybrid search, watching transactions as they land, and running the AML/KYC checks. Whatever it concludes comes with a plain explanation an analyst can actually sign off on.

Python
LLM agents
RAG
Qdrant
PostgreSQL
React

AI / MLLiveML & backend

2026

RideSync+

Puts Uber, Bolt, Yango, and Shaxi side by side using real road distances from Google, forecasts surge with a RandomForest model, and streams live prices to a Flutter app over WebSockets with push alerts. It was my final-year project, and it ships with a full test suite.

Python
FastAPI
scikit-learn
WebSocket
Flutter
Redis

BackendProductionBackend & ML

2026

Araba — University AI Assistant

A WhatsApp assistant for University of Ghana students. It answers questions about fees, hostels, admissions, and the calendar in English or Twi, and every answer is grounded in the university’s own documents. The LLM and the messaging layer are both swappable, so another school could pick it up without a rewrite.

Python
FastAPI
pgvector
Redis
RAG
WhatsApp Cloud API

AI / MLProductionML & backend

2026

Egg Commerce Platform

An e-commerce setup where the storefront, the admin dashboard, and the mobile app all run off one Laravel API instead of three separate backends. It works out delivery pricing by district and takes Paystack payments over mobile money and card.

Laravel
Next.js
React Native
PostgreSQL
Paystack

Full-stackProductionFull-stack

2025

Payment Voucher System

Lets an organization raise, approve, and pay supplier vouchers through an approval chain you can configure to however many signatures you need. It works out Ghana/GRA tax, prints the official PDF slips, and keeps a record of every step that nobody can quietly go back and edit.

Spring Boot
React
PostgreSQL
Flyway
OpenPDF

Full-stackProductionFull-stack

Experience

Where I have worked. Most of it has been at AfricodeLab, the company I co-founded, with some consulting and a stint in a research lab alongside.

Sep 2025 – Dec 2025

Data Intelligence and Swarm Analytics Laboratory (DISAL)

AI / ML Research Engineer & Project Supervisor

Led applied medical-AI work and supervised intern teams building enterprise and academic platforms, guiding architecture, fine-tuning, and responsible-AI practice.

Led MedGemma fine-tuning for diabetic-retinopathy detection, chest X-ray classification with automated radiology-report generation, and equitable dermatological diagnosis on African skin tones.
Owned model-architecture decisions, dataset preparation, evaluation strategy, and ethics review across 10+ healthcare-focused ML projects.
Supervised intern teams delivering HR, academic, school, hostel, and admission management systems in Python, React, and PHP.
Ran technical reviews and progress evaluations to hold projects to quality, scalability, and delivery targets.

2023 – Present

AfricodeLab

AI / ML Engineer

Design, build, and ship production LLM and machine-learning systems, from document understanding and chatbots to RAG-grounded retrieval over private data.

Built and deployed LLM solutions for document understanding, conversational assistants, and intelligent automation.
Fine-tuned transformer models on domain data and implemented Retrieval-Augmented Generation with FAISS for real-time proprietary retrieval.
Developed end-to-end ML pipelines: preprocessing, training, evaluation, and cloud deployment.
Optimized inference and serving through containerization, API abstraction, and cloud infrastructure.

2023 – 2025

AfricodeLab

Senior Software Developer

Architected a production microservices ecosystem with Spring Boot and cloud-native patterns.

Designed a full microservices ecosystem: Netflix Eureka service discovery, an API gateway, and centralized Spring Cloud Config backed by Git.
Built a centralized authentication and authorization server for secure service-to-service communication.
Developed core domain services including Delivery Management and Event Processing.
Improved scalability, fault tolerance, and deployment flexibility across the platform.

2023 – Present

AfricodeLab

Associate Software Developer

Deliver business-critical applications and keep production systems observable and governed.

Served as lead developer for a national-scale Election Management System, from system design to implementation.
Built Payroll Management and Payment Voucher systems with full reporting.
Implemented API governance with WSO2 and traced production issues with Glowroot APM.

2023 – Present

AfricodeLab

Database Manager & Administrator

Own the design, performance, and integrity of client application databases across environments.

Designed scalable database architectures for client-facing applications on MySQL, Oracle, and PostgreSQL.
Cut query execution times by up to 40% through indexing, query rewriting, and schema optimization.
Established backup, recovery, and disaster-recovery strategies and ran live, zero-downtime migrations.

2022 – 2024

Independent consultancy

Java Software Developer

Built backend services for a logistics platform with a focus on throughput and maintainability.

Built RESTful APIs and microservices with Java and Spring Boot.
Integrated third-party services and optimized queries, improving throughput by 35%.
Led backend refactoring that reduced technical debt.

2021 – 2025

Independent consultancy

Data Analyst

Delivered socio-economic, energy, and environmental analyses supporting evidence-based policy and sustainability planning.

Studied the socio-economic and ecological impact of sand mining in the South Tongu District using EPA methods and inferential statistics.
Analyzed household energy use, LPG adoption, and the feasibility of biomass-briquette alternatives.
Built a fuel-price prediction model for Ghana (Jun 2023 – May 2024) using time-series analysis in Python.
Produced stakeholder reporting with Python, Power BI, and Tableau.

Research

My published work, and the questions I keep coming back to when the building stops and the science starts.

Peer-reviewedBook chapter·2026

A Hybrid BPSO-PSO Optimized Multilayer Perceptron Framework for Enhanced Heart Disease Prediction

Nathanael Ayirebaje Azuponga, Jumah Musah, Courage Adzewoda, Noble Eselase Vulley, Justice Kwame Appati, Michael Agbo Tettey Soli.

Innovative Computing and Communications (ICICC 2025). Lecture Notes in Networks and Systems, Springer Nature Switzerland, 2026, pp. 254–264.

A multilayer-perceptron framework tuned by a hybrid Binary Particle Swarm Optimization and Particle Swarm Optimization scheme, applied to feature selection and hyperparameter search to improve the accuracy of heart-disease prediction.

View on SpringerLinkDOI: 10.1007/978-3-032-30005-8_21

Current interests

Medical imaging & responsible AI
Retrieval-augmented generation
Graph & swarm-based learning
Applied ML for public policy

Recent applied work includes MedGemma fine-tuning for medical imaging and a graph-pooling Vision Transformer for histopathology.

Stack

The tools I actually reach for. I am deepest in the JVM and Python worlds, with databases sitting under most of what I do.

Languages

Java
Python
TypeScript
Go
C#
PHP
C++
PL/SQL
SQL
JavaScript
VB.Net

Frameworks

Spring Boot
Next.js
React
Vue.js
Laravel
Django
FastAPI
Gin
.NET
JavaFX

AI / ML

PyTorch
LLMs
RAG
FAISS
Qdrant
Fine-tuning
NLP
Computer Vision
MedGemma

Data & infra

PostgreSQL
Oracle
MySQL
Docker
Kubernetes
Kafka
RabbitMQ
Redis
WSO2

Practices

Microservices
REST / gRPC
CI/CD
System design
Observability
Database tuning

Education

2019 – 2023

BSc Computer Science

University of Ghana—With Applied Mathematics.

2022 – 2023

Professional Database Technology

IPMC—Database management and administration.

Get in touch

I am open to contract and full-time roles in software, ML, or database work, and to research collaboration. Email is the quickest way to reach me.

Got something you are building, or a paper you want a hand with? I would like to hear about it.

Email: eselasenobleson@gmail.com
Phone: +233 553 851 758
GitHub: Eselase-Noble
LinkedIn: noble-vulley

Accra, Ghana