Callum Cummins

Callum Cummins

Software Engineer with commercial experience building full-stack applications, automation systems, and AI-powered tools in production - including LLM-driven systems that cut AML investigation time from hours to minutes.

View workGet in touchDownload CV

About

About me

Software engineer at bet365 and First Class CS graduate. I like making machines do useful things.

I graduated with First Class Honours in Computer Science from Keele University, where I focused on the intersection of artificial intelligence and practical software development.

My dissertation project - a full-stack fitness tracking application with predictive ML capabilities - earned a First Class grade and a 4.2/5 user satisfaction rating through iterative, user-led development.

I now work at bet365 as an AI Engineer in Business Systems Solutions, building production systems like a global AML investigation platform and LLM-powered reporting workflows that cut investigation time from hours to minutes.

Outside work I keep building - from fine-tuning BERT for phishing detection at 97.7% validation accuracy to a voice-controlled AI home assistant - always with the goal of turning research-grade AI into software people can actually use.

AI Engineer at bet365

LLM-powered production systems for business operations

First Class Honours

BSc Computer Science from Keele University

Full-stack development

Next.js, TypeScript, Python, and C# in production

Certified

AWS, Codecademy, and HackerRank certifications

Education

BSc Computer Science

Keele University · First Class Honours

Sep 2021 - July 2025
Software Development ManagementAdvanced Databases and ApplicationsCommunications and NetworksComputational and Artificial Intelligence

Dissertation: First Class grade of 80%. Gym Goer Web App: Developed a full-stack fitness tracking application with predictive ML capabilities, achieving 4.2/5 user satisfaction and 90% recommendation rate.

Level 3 Extended Diploma in IT

Coleg Cambria · Merit, Merit, Distinction (MMD)

Sep 2019 - July 2021
Computer SystemsComputer NetworksCyber Security3D AnimationGame DesignIT Project Management

Certifications

Beyond code

  • Bouldering - university competitions; problem-solving on the wall
  • Tutoring - volunteer programming tutor for local students
  • Fitness - regular training; consistency over intensity

Skills

Skills & expertise

Languages

PythonJavaScriptTypeScriptC# (.NET)PHPSQLHTML/CSS

Frameworks

ReactNext.jsViteTailwind CSSFlaskFastAPIPySide6 (Qt)

Libraries

styled-componentsAnt Designscikit-learnPyTorchjQueryTkinter

I use Python, TypeScript, and C# professionally to build full-stack applications and integrate AI models into production systems.

Projects

Featured projects

Built to answer 'what if?' - AI experiments, full-stack apps, and coursework that got out of hand.

AI/ML

Jarvis - AI Home Assistant

Voice-controlled AI home assistant built on Microsoft Semantic Kernel, shipping a Rich terminal UI and a PySide6 desktop app with a full voice pipeline. Work in progress. "Is that all, sir?"

PythonSemantic KernelOllamaOpenAI APIPySide6 (Qt)faster-whisperopenWakeWordedge-tts
  • "Hey Jarvis" wake-word pipeline: speech-to-text, agent, text-to-speech, then a natural follow-up loop
  • Dual-provider: local Ollama and cloud OpenAI run simultaneously, switchable live by voice with isolated per-provider history
  • Function-calling plugins for Chrome browser control, Tavily web search, notes/todos, screenshots, and image generation
  • Provider-themed animated orb overlay and persistent image viewer in the desktop app
  • Preloaded Whisper singleton removing a ~6s per-request delay; covered by pytest, ruff, and mypy
Gym Goer Web App - Dissertation Project

AI/ML · Web Development

Gym Goer Web App - Dissertation Project

Full-stack fitness tracking application with predictive ML capabilities using custom AI models for exercise progress prediction.

HTML/CSSPHPPHPmlJavaScriptTailwind CSSMySQLChart.js
  • Custom AI model using SVR/Linear regression
  • Google Maps and OpenWeather API integration as well as own RESTful API for saving running routes
  • Agile development with user feedback iterations
  • 4.2/5 user satisfaction rating
  • 90% recommendation rate
Code
Phishing Email Detector

AI/ML · Data Analysis

Phishing Email Detector

Advanced email security application using BERT for phishing detection with high accuracy classification.

PythonPyTorchBERTTkinterPandasHugging Face
  • Fine-tuned BERT model on CUDA GPUs
  • 97.7% validation accuracy (0.98 precision, 0.97 recall) on 3.7K+ samples
  • OCR and clipboard input support
  • End-to-end data pipeline
  • Real-time classification
Code
Movie Explorer

Web Development · AI/ML

Movie Explorer

Modern React + TypeScript movie discovery app built with styled-components and Ant Design, featuring GPT-powered summaries served from a Vercel serverless function.

ReactTypeScriptVitestyled-componentsAnt DesignTanStack QueryReact RouterAxiosOpenAI APITMDB API
  • AI bullet-point summaries per movie via an OpenAI serverless endpoint
  • Trending, top-rated, and obscure movie listings from TMDB
  • Instant search with dynamic filtering options
  • Watchlist and star ratings
  • Folder-per-component architecture with styled-components and AntD
CodeLive demo

More projects, contributions, and code samples on GitHub.

Experience

Work experience

Where the code ships to production and real people depend on it.

  1. Junior Business Systems Solutions AI Engineer

    bet365 · Manchester, UK

    Oct 2025 - Present

    Building full-stack and AI-powered systems in production, from a global AML investigation platform to LLM-driven reporting workflows.

    • Built and delivered a Next.js/TypeScript frontend for a global AML investigation platform used across multiple regions, consolidating fragmented data sources into a single interface and reducing subject lookup and analysis time from several hours to ~8 minutes per case
    • Co-developed an LLM-powered AML reporting workflow (Python, Azure OpenAI) that generates structured investigation reports from raw data, increasing analyst throughput by more than 10x while improving consistency across jurisdiction-specific reports
    • Rapidly upskilled in C# to extend a legacy enterprise system, delivering an auto-generated risk assessment form driven by Change Request component criticality, plus the supporting UI modal and RESTful CRUD endpoints
    • Automated weekly timesheet reporting in Python - aggregating submissions into a templated Excel workbook with dynamic pivot tables, notifying non-compliant staff automatically, and generating recurring attendance dashboards
    • Diagnosed and resolved a production CSV export failure caused by missing tzdata in a minimal Alpine container image, restoring correct Europe/London timezone handling and full output

Contact

Get in touch

Got a project, a question or just want to chat about tech? Let's talk about it.

Email

callumcummins28@gmail.com

GitHub

CallumC28

LinkedIn

callum-cummins