# Owen Cheung — AI Engineer AI Engineer at LexisNexis Risk Solutions, building human-governed workflows for fraud-model optimisation\. Final-year Computer Science & AI student at the University of Bath\. I'm Owen, an AI Engineer at LexisNexis Risk Solutions and a final-year Computer Science & AI student at the University of Bath\. I stayed on as a contractor after my industrial placement to develop a self-initiated prototype into a funded internal pilot\. I care about systems that learn: representation learning, embeddings with the right geometry, and agentic systems that do real work\. I’m heading toward AI research and engineering\. Away from the screen I snowboard with Bath Snowsports, pull a lot of espresso, and build mechanical keyboards — which is how I ended up typing at 193 wpm (and designing TypeForge)\. Contact: oc608@bath\.ac\.uk LinkedIn: GitHub: ## Experience ### AI Engineer (Agentic AI) — LexisNexis Risk Solutions Aug 2026 — present · Contract Human-governed fraud-model optimisation workflows; funded internal pilot building toward production\. ### Data Scientist — LexisNexis Risk Solutions Jul 2025 — Aug 2026 · Industrial placement Transaction analysis, two fraud-model optimisations, self-supervised representation learning and an agentic working demo\. ### Full-Stack Developer — Dish'D Jan 2024 — Feb 2025 Built a social cooking app end-to-end with Django \+ Flutter; led technical decisions\. ### System Tester — Kinetix Jul 2024 — Aug 2024 QA for Census & Statistics Department systems — validated functionality against spec\. ### AI Project Intern — DXC Technology Jul 2022 — Aug 2022 Drafted technical proposals for enterprise bids (AI-assisted mapping, OpenBIM\.AI)\. ## Education University of Bath — BSc (Hons) Computer Science & Artificial Intelligence, with placement · Sept 2023 — 2027 (expected) · Expected 2:1 Wellington College — A-Levels — Maths, Further Maths, Physics, Computer Science · Aug 2021 — Aug 2023 · ## Skills - AI / ML: PyTorch, Contrastive learning, Hyperbolic embeddings, Agentic systems, Deep learning - Languages: Python, TypeScript, Haskell, Dart, SQL - Frameworks: React / Node, Django, Flutter, Next\.js - Data: SQL, Snowflake, Statistical modelling, Data analysis - Cloud / AI: Azure OpenAI, Azure Foundry and AWS S3 (workshop experience) ## Interests - Snowboarding: Carving and freestyle with Bath Snowsports — away from the screen\. - Specialty coffee: Chasing brew methods and flavour\. - Mechanical keyboards: Built several from scratch; reached 193 wpm\. ## Projects # LexisNexis — Applied AI Internal pilot · toward production · Jul 2025 — present Role: AI Engineer (Agentic AI) · previously Data Scientist Stack: Python, SQLite, DVC, Papermill, LightGBM, Snowflake, PyTorch During my placement I built a working demo for fraud-model optimisation\. I was retained as an AI engineering contractor to develop the capital-funded internal pilot toward production\. ## Context Fraud-model optimisation combines analysis, modelling and decisions that need accountable human review\. ## My contribution Initiated a working agentic prototype during my placement, then stayed on as a contractor to develop the funded internal pilot\. ## Approach - Custom Python orchestration and reusable Copilot skills coordinate work with persistent SQLite state\. - Audit trails and mandatory review gates keep human judgement in the workflow\. - DVC and Papermill make notebook-based work recoverable; LightGBM discovers candidate rules, with constrained logistic regression for policy weighting\. ## Highlights - Custom Python orchestration, reusable Copilot skills, persistent SQLite state, audit trails and mandatory human review gates\. - Recoverable DVC/Papermill workflows with LightGBM candidate-rule discovery and constrained logistic-regression policy weighting\. - Placement work included two fraud-model optimisations and analysis of billions of transaction records using Python, SQL and Snowflake\. - Researched self-supervised fraud representations using graph embeddings, contrastive learning and non-Euclidean geometry\. ## Evidence - Working demo delivered to the AI engineering team by the end of the placement\. - Retained as an AI engineering contractor in August 2026 to develop a capital-funded internal pilot\. - Two fraud-model optimisations completed during the earlier placement\. ## Limitations - Employer-confidential work: no source code, transaction data or internal evaluation results are published\. - This describes a pilot building toward production, not a launched production platform\. - Descriptions are owner-supplied; no independently verified performance uplift is claimed\. Source: Owner-supplied professional and project descriptions; earlier non-conflicting portfolio material retained\. Not independent verification\. # TypeForge In development · Jul 2025 — present Role: Solo developer Stack: React, Node\.js, TypeScript, Keystroke analytics I am developing a typing application that tracks cadence, keystrokes and accuracy, with AI-driven drills designed and implemented to adapt to user weaknesses\. It comes from building mechanical keyboards and reaching 193 wpm\. A public demo is available; the product remains in development, with no public evaluation or full product release claimed\. Live demo: ## Context Typing practice can focus on a headline speed rather than the particular weaknesses a person needs to practise\. ## My contribution Designing and building a React/Node\.js typing application, including implemented AI-driven adaptive drills\. ## Approach - Developing real-time analytics for cadence, keystrokes and accuracy\. - Adaptive drills target user weaknesses\. - Personal typing and keyboard-building experience informs the product direction\. ## Highlights - Designed and implemented adaptive AI-driven drills\. - Developing real-time cadence, keystroke and accuracy analytics\. - A personal exploration of more targeted typing practice\. ## Evidence - Adaptive AI-driven drills designed and implemented, as described in my current project record\. ## Limitations - A public demo is available; the product is still in development, not a full product release\. - No measured learning uplift, timing precision or model benchmark is published\. Source: Owner-supplied professional and project descriptions; earlier non-conflicting portfolio material retained\. Not independent verification\. # Sortify Earlier project · 2024 Role: Backend \+ recommendations Stack: Python, Spotify API, Recommendation A Spotify-API app that sorts and recommends playlists by genre, mood and danceability\. I built the backend recommendation logic on top of Spotify's audio-feature data to surface personalised picks for how a playlist actually feels\. ## Context Organising music around genre, mood and danceability\. ## My contribution Built backend recommendation logic using Spotify audio features\. ## Approach - Python backend with the Spotify API\. - Audio-feature-based playlist organisation and personalised recommendations\. ## Highlights - Clusters tracks by audio features — mood, danceability, genre\. - Personalised recommendations from listening signals\. - Python backend against the Spotify Web API\. ## Evidence - Project summary retained from earlier portfolio work\. ## Limitations - No public evaluation, repository or current live service is supplied\. - This is historical project work, not a claim about current Spotify API availability\. Source: Owner-supplied professional and project descriptions; earlier non-conflicting portfolio material retained\. Not independent verification\. # Knowtrients Team project · pilot tested · Oct 2024 — May 2025 Role: Full-stack \+ Scrum Stack: Django, Flutter / Dart, Agile / Scrum A micronutrient-tracking and wellbeing app built in a team of 8 using Scrum\. I implemented recipe parsing and nutrition analysis end-to-end with Django and Flutter, and helped run sprint planning and stakeholder testing — we onboarded 20\+ pilot users\. ## Context A micronutrient-tracking and wellbeing app built by a team of eight\. ## My contribution Implemented recipe parsing and nutrition analysis across Django and Flutter, and helped coordinate sprint planning and stakeholder testing\. ## Approach - Full-stack recipe parsing and nutrition analysis\. - Agile Scrum collaboration and stakeholder testing\. ## Highlights - Recipe parsing \+ nutrition analysis, end to end\. - Team of 8 on a real Scrum cadence\. - 20\+ pilot users through stakeholder testing\. ## Evidence - Team of eight\. - 20\+ pilot users through stakeholder testing\. ## Limitations - Pilot participation is not a claim of retention or health outcomes\. - No public repository or live deployment is supplied\. Source: Owner-supplied professional and project descriptions; earlier non-conflicting portfolio material retained\. Not independent verification\. # Dish'D Previous product work · Jan 2024 — Feb 2025 Role: Full-Stack Developer Stack: Django, Flutter / Dart, Auth, Feeds A social cooking app where people share recipes and meal inspiration\. I built core features — authentication, content sharing and interactive feeds — with Django and Flutter, and led technical decisions on scalability, usability and performance\. ## Context A social cooking mobile application for recipes and meal inspiration\. ## My contribution Developed core features and led technical decisions on scalability, usability and performance\. ## Approach - Django backend with Flutter/Dart mobile client\. - Authentication, sharing and interactive feeds\. ## Highlights - Auth, content sharing and interactive feeds\. - Led technical decisions on scalability \+ performance\. - Django backend, Flutter/Dart mobile client\. ## Evidence - Full Stack Developer, January 2024 to February 2025\. ## Limitations - No public adoption metrics, repository or live deployment is supplied\. Source: Owner-supplied professional and project descriptions; earlier non-conflicting portfolio material retained\. Not independent verification\.